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

    Neuronpedia

    INDEX
    Explanations

    deadlines and expirations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    QUI
    -0.07
    항
    -0.07
    쑥
    -0.07
     Navigate
    -0.07
    なくなった
    -0.07
    Tre
    -0.07
    羝
    -0.07
    缩
    -0.06
    申
    -0.06
    =read
    -0.06
    POSITIVE LOGITS
    ATAL
    0.07
    프로그램
    0.07
    _almost
    0.07
    真正
    0.06
    _dirty
    0.06
    外卖
    0.06
    Inlining
    0.06
    Styles
    0.06
    ~":"
    0.06
    _UTF
    0.06
    Act Density 0.016%

    No Known Activations