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

    Neuronpedia

    INDEX
    Explanations

    particular

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    umps
    -0.07
    ukan
    -0.07
    итет
    -0.07
    ISED
    -0.07
     Fraud
    -0.07
    eligible
    -0.07
    ynamic
    -0.07
    WA
    -0.06
    umped
    -0.06
     fık
    -0.06
    POSITIVE LOGITS
    Vac
    0.07
     Bern
    0.07
     Προ
    0.06
     ช
    0.06
     Báo
    0.06
     Dabei
    0.06
     Taj
    0.06
     海
    0.06
    Spain
    0.06
     câ
    0.06
    Act Density 0.013%

    No Known Activations