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

    Neuronpedia

    INDEX
    Explanations

    Code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .after
    -0.07
    hra
    -0.07
    _Dec
    -0.07
    _Mod
    -0.06
    电脑
    -0.06
    /documentation
    -0.06
     Sensors
    -0.06
     �
    -0.06
    inction
    -0.06
    Honda
    -0.06
    POSITIVE LOGITS
     Beatles
    0.07
     суспіль
    0.06
     Territories
    0.06
     kẻ
    0.06
     имму
    0.06
    _rect
    0.06
    立て
    0.06
     إذا
    0.06
     прик
    0.06
    込み
    0.05
    Act Density 0.010%

    No Known Activations