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

    Neuronpedia

    INDEX
    Explanations

    symbols and syntax elements commonly used in programming and coding contexts

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

    code punctuation and operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.71
     незавершена
    -0.71
     للمعارف
    -0.69
    WithIOException
    -0.68
     Chwiliwch
    -0.67
     betweenstory
    -0.66
    tvguidetime
    -0.65
    LookAnd
    -0.63
    __':
    -0.63
    IsContent
    -0.63
    POSITIVE LOGITS
     Lath
    0.36
    1
    0.35
    --
    0.35
    ---
    0.35
    xaxis
    0.34
    örung
    0.34
     squire
    0.33
    <eos>
    0.33
    case
    0.32
    0
    0.32
    Act Density 0.003%

    No Known Activations