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

    Neuronpedia

    INDEX
    Explanations

    Changes and trends

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     als
    -0.06
     lối
    -0.06
    VEC
    -0.06
    J
    -0.06
    .hist
    -0.06
    igon
    -0.06
    71
    -0.06
    _history
    -0.06
     matches
    -0.06
    这一
    -0.06
    POSITIVE LOGITS
     actionTypes
    0.07
    短
    0.06
    scheduler
    0.06
    栏
    0.06
     Stat
    0.06
    .hour
    0.06
    例
    0.06
    oeff
    0.06
     单
    0.06
    Kid
    0.06
    Act Density 0.158%

    No Known Activations