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

    Neuronpedia

    INDEX
    Explanations

    references to literature and influential works

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

    Book titles

    np_acts-logits-general · gemini-2.0-flash

    start of titles and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '/',
    -0.52
    iseaux
    -0.46
     aktivitet
    -0.45
    anum
    -0.43
    bildet
    -0.43
     continued
    -0.43
    -
    -0.41
     सु
    -0.41
    /");
    -0.41
    asje
    -0.41
    POSITIVE LOGITS
    windowFixed
    1.01
    LookAnd
    0.91
    IndentedString
    0.84
    MessageOf
    0.84
     Мексичка
    0.80
    تقاوى
    0.80
     Majefty
    0.76
     Италијани
    0.75
     Efq
    0.75
    脚注の使い方
    0.73
    Act Density 0.110%

    No Known Activations