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

    Neuronpedia

    INDEX
    Explanations

    @app

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    送达
    -0.08
    export
    -0.08
    _UINT
    -0.07
    事业单位
    -0.07
    vron
    -0.07
    write
    -0.07
    .ut
    -0.07
    Delete
    -0.07
    _wf
    -0.07
    仙境
    -0.07
    POSITIVE LOGITS
     backing
    0.07
     Compared
    0.07
     nestled
    0.06
     thước
    0.06
    这边
    0.06
    갘
    0.06
     ос
    0.06
     crushed
    0.06
     мас
    0.06
     示例
    0.06
    Act Density 0.001%

    No Known Activations