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

    Neuronpedia

    INDEX
    Explanations

    factors related to mathematical operations and relationships

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

    negative values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     سكانية
    -0.66
     ProtoMessage
    -0.63
    новниш
    -0.63
    oredCriteria
    -0.63
     kapturem
    -0.59
    存于互联网档案馆
    -0.57
    EDEFAULT
    -0.56
    GraphicsUnit
    -0.55
    antası
    -0.54
    writeFieldEnd
    -0.54
    POSITIVE LOGITS
    (-
    0.52
     negative
    0.48
    Negative
    0.47
     Negative
    0.45
    =-
    0.43
    [-
    0.43
     (-
    0.42
    +(-
    0.42
     отрица
    0.38
     (−
    0.38
    Act Density 0.725%

    No Known Activations