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

    Neuronpedia

    INDEX
    Explanations

    numerical identifiers or sequences

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

    Punctuation and symbols

    np_acts-logits-general · gemini-2.0-flash

    numbers, punctuation and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rhestr
    -1.25
     itſelf
    -1.19
    ValueStyle
    -1.17
     myſelf
    -1.16
     fubject
    -1.13
     reaſon
    -1.03
     ſeveral
    -1.03
     neceff
    -1.03
     faſt
    -1.01
    #
    -1.01
    POSITIVE LOGITS
     
    0.80
     (
    0.51
    (
    0.51
    <eos>
    0.45
     -
    0.45
     O
    0.44
    /
    0.44
     near
    0.42
    -
    0.41
    )
    0.41
    Act Density 0.132%

    No Known Activations