Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to individuals or entities involved in historical or legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following articles or numbers

    np_acts-logits-general · gemini-2.0-flash

    on the one hand

    np_acts-logits-general · gemini-2.5-flash-lite

    high-frequency function words and structural markers typical of formal/technical prose, including math/citation formatting tokens.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    WebElementEntity
    -0.47
     îna
    -0.40
     AssemblyTitle
    -0.36
     atve
    -0.35
    Bakgrunnsstoff
    -0.35
     adelantado
    -0.33
     ivelany
    -0.32
     Glaubens
    -0.32
     medži
    -0.31
     صوتيه
    -0.31
    POSITIVE LOGITS
     queſto
    0.70
    [@BOS@]
    0.65
    <unused14>
    0.64
    <unused28>
    0.64
    <unused8>
    0.64
    <unused51>
    0.64
    <unused41>
    0.64
    <unused79>
    0.64
    <unused43>
    0.64
    <pad>
    0.63
    Act Density 4.197%

    No Known Activations