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

    Neuronpedia

    INDEX
    Explanations

    relationships and interactions between characters

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

    pronoun followed by a verb or noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sebenar
    -0.31
     betreft
    -0.28
     cumplimiento
    -0.27
     daarbij
    -0.27
     dalších
    -0.27
     υπό
    -0.26
     kaikki
    -0.25
     selve
    -0.25
     requerida
    -0.25
     stej
    -0.25
    POSITIVE LOGITS
    ésultats
    0.72
     geſch
    0.69
    <unused52>
    0.65
    <unused8>
    0.65
    <unused14>
    0.65
    <unused51>
    0.64
    <unused68>
    0.64
    <unused41>
    0.64
    [@BOS@]
    0.64
    <unused16>
    0.64
    Act Density 0.061%

    No Known Activations