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

    Neuronpedia

    INDEX
    Explanations

    dates and times

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aperture
    -0.07
    _TM
    -0.07
    ≾
    -0.07
     Autof
    -0.07
    向下
    -0.06
    建て
    -0.06
     Judicial
    -0.06
    덟
    -0.06
    leigh
    -0.06
     Quý
    -0.06
    POSITIVE LOGITS
    侄
    0.08
    BERT
    0.07
    trying
    0.07
    닉
    0.07
    +=(
    0.06
    ナー
    0.06
    Thomas
    0.06
    książ
    0.06
    Jacob
    0.06
    memcpy
    0.06
    Act Density 0.003%

    No Known Activations