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

    Neuronpedia

    INDEX
    Explanations

    due to numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cognitive
    0.40
     energ
    0.39
     euph
    0.39
    ափ
    0.39
    unary
    0.38
     ليست
    0.37
     జాగ్ర
    0.37
     Mao
    0.37
    ಷ್ಟು
    0.37
     HLA
    0.37
    POSITIVE LOGITS
    评价
    0.41
    ině
    0.37
     समझ
    0.37
    Fact
    0.37
    Facts
    0.36
     नेशनल
    0.36
    kais
    0.36
    їз
    0.35
    olgens
    0.35
    SB
    0.35
    Act Density 0.018%

    No Known Activations