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

    Neuronpedia

    INDEX
    Explanations

    above

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tấn
    -0.07
     связи
    -0.07
     gouver
    -0.07
     circumstances
    -0.07
     Simon
    -0.06
     fortunes
    -0.06
    protobuf
    -0.06
    uart
    -0.06
     sympt
    -0.06
    ма
    -0.06
    POSITIVE LOGITS
     Weld
    0.06
    اول
    0.06
     go
    0.06
     QS
    0.06
     nameof
    0.06
    恵
    0.06
     onPostExecute
    0.06
    -fill
    0.06
    Leading
    0.06
     leading
    0.06
    Act Density 0.007%

    No Known Activations