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

    Neuronpedia

    INDEX
    Explanations

    awake

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ·
    -0.07
     Pyongyang
    -0.07
    全家
    -0.07
     reproduced
    -0.07
    .Center
    -0.07
    垟
    -0.07
     Detroit
    -0.07
    -demand
    -0.07
    awy
    -0.06
    .invalidate
    -0.06
    POSITIVE LOGITS
     paragraph
    0.07
    蓬勃
    0.07
     debates
    0.06
    个体
    0.06
    _hint
    0.06
    Введите
    0.06
    param
    0.06
    יז
    0.06
    冽
    0.06
     Ibid
    0.06
    Act Density 0.009%

    No Known Activations