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

    Neuronpedia

    INDEX
    Explanations

    markers indicating the beginning of a document

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

    Text following "Q:" or a scientific field

    np_acts-logits-general · gemini-2.0-flash

    hili, Soh, Schiltz types of names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.47
    מצא
    -0.46
     com
    -0.46
     mạch
    -0.45
    v
    -0.44
     mil
    -0.43
    گاری
    -0.43
    שא
    -0.43
    νας
    -0.43
    deniz
    -0.43
    POSITIVE LOGITS
    存于互联网档案馆
    0.86
     typelib
    0.85
     esternos
    0.85
     ModelExpression
    0.83
    sidemargin
    0.80
    enumi
    0.79
    CloseOperation
    0.78
    UrlResolution
    0.78
    帖最后由
    0.78
    MigrationBuilder
    0.74
    Act Density 0.074%

    No Known Activations