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

    Neuronpedia

    INDEX
    Explanations

    Data and codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    supported
    -0.07
    رت
    -0.06
    _);↵↵
    -0.06
     monstrous
    -0.06
     initWithFrame
    -0.06
    ]initWithFrame
    -0.06
     cleanly
    -0.06
    lili
    -0.06
     ứng
    -0.06
    _IO
    -0.06
    POSITIVE LOGITS
     ниж
    0.07
     осіб
    0.07
    //(
    0.07
    UST
    0.06
    ']).
    0.06
     للأ
    0.06
    人員
    0.06
     Spacer
    0.06
    шая
    0.06
     demo
    0.06
    Act Density 0.073%

    No Known Activations