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

    Neuronpedia

    INDEX
    Explanations

    public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LU
    -0.07
    .lines
    -0.07
    薰
    -0.07
     certifications
    -0.06
     curse
    -0.06
    写字
    -0.06
    留
    -0.06
    监护
    -0.06
    HEST
    -0.06
    女主
    -0.06
    POSITIVE LOGITS
    WebRequest
    0.08
     indiscrim
    0.08
     Casual
    0.07
    .btnExit
    0.07
     Когда
    0.07
    เขา
    0.07
     cela
    0.06
     것이다
    0.06
     циф
    0.06
    dür
    0.06
    Act Density 0.002%

    No Known Activations