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

    Neuronpedia

    INDEX
    Explanations

    code installation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pwd
    -0.07
     hous
    -0.07
     três
    -0.06
     Feinstein
    -0.06
     zatím
    -0.06
    _gid
    -0.06
    aturas
    -0.06
    bedPane
    -0.06
    Jak
    -0.06
     Rou
    -0.06
    POSITIVE LOGITS
    .code
    0.07
    NSNotificationCenter
    0.07
    167
    0.06
    ishment
    0.06
     medicine
    0.06
    .qt
    0.06
    كي
    0.06
    31
    0.06
    لیت
    0.06
    」「
    0.06
    Act Density 0.006%

    No Known Activations