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

    Neuronpedia

    INDEX
    Explanations

    headings and structural markers in formatted text

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

    section identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.92
     queſta
    -0.81
    ագրություններ
    -0.73
    migrationBuilder
    -0.71
     незавершена
    -0.69
    WebElementEntity
    -0.69
    niſſe
    -0.67
     betweenstory
    -0.67
    <unused28>
    -0.66
    IsMutable
    -0.66
    POSITIVE LOGITS
    übers
    0.28
    D
    0.28
    CloseOperation
    0.27
    Viitteet
    0.27
    czej
    0.27
    和
    0.26
    DeclareMath
    0.26
    âche
    0.26
    #
    0.26
    t
    0.25
    Act Density 0.006%

    No Known Activations