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

    Neuronpedia

    INDEX
    Explanations

    units and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     understands
    0.44
     enumer
    0.38
     nume
    0.37
     tantas
    0.37
     Huge
    0.37
    フィール
    0.37
    同意
    0.36
     chó
    0.36
     ferocious
    0.36
    Judging
    0.35
    POSITIVE LOGITS
    MA
    0.44
     攵
    0.41
    LA
    0.39
    MIS
    0.38
    NA
    0.38
    IR
    0.37
    DR
    0.37
     MeV
    0.37
    MS
    0.37
    efficacité
    0.37
    Act Density 0.000%

    No Known Activations