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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     результате
    -0.06
     dsp
    -0.06
     Padres
    -0.06
    annual
    -0.06
    .You
    -0.06
    RUN
    -0.06
    喜欢
    -0.06
    يز
    -0.06
     zveřej
    -0.06
     serviços
    -0.06
    POSITIVE LOGITS
    -Disposition
    0.06
     irrit
    0.06
    ích
    0.06
     decad
    0.06
    templ
    0.06
     vanity
    0.06
     puberty
    0.06
     donation
    0.06
    Occurs
    0.06
     madd
    0.06
    Act Density 0.040%

    No Known Activations