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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and positive sentiments

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

    lucky and alive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     خارجية
    -0.43
    ifrance
    -0.43
    Hauptartikel
    -0.42
     Chwiliwch
    -0.42
    <?
    -0.39
    istible
    -0.39
    育
    -0.39
    scrollY
    -0.39
    MigrationBuilder
    -0.39
    atchewan
    -0.39
    POSITIVE LOGITS
     spared
    0.56
     saved
    0.53
     Saved
    0.52
     escape
    0.50
     Rettung
    0.48
     fortunate
    0.47
     lucky
    0.47
     ModelExpression
    0.46
     relief
    0.46
     thoát
    0.46
    Act Density 0.134%

    No Known Activations