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

    Neuronpedia

    INDEX
    Explanations

    expressions of human experience and interaction

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

    always does

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.58
    исленность
    -0.53
     חיצוניים
    -0.52
    InSection
    -0.51
    PropertyGroup
    -0.50
     Trains
    -0.47
    الحياه
    -0.46
    STI
    -0.46
    StringCopy
    -0.46
     старости
    -0.45
    POSITIVE LOGITS
    出版年
    0.41
     utafitiHapana
    0.41
    VYMaps
    0.34
    httphttps
    0.33
     contextLoads
    0.33
    Activité
    0.33
     peuples
    0.33
     continuidad
    0.32
    exitRule
    0.32
    postsleuth
    0.31
    Act Density 0.069%

    No Known Activations