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

    Neuronpedia

    INDEX
    Explanations

    candidate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disastrous
    -0.07
    ‡
    -0.07
     medios
    -0.07
    inp
    -0.06
     wrongful
    -0.06
    ян
    -0.06
     Prec
    -0.06
     Romeo
    -0.06
     CEOs
    -0.06
     undesirable
    -0.06
    POSITIVE LOGITS
    Ｅ
    0.08
    cadena
    0.07
     Charger
    0.06
    Interceptor
    0.06
    /chart
    0.06
    _schedule
    0.06
    .titleLabel
    0.06
    灯
    0.06
     菲律宾
    0.06
    aber
    0.06
    Act Density 0.021%

    No Known Activations