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

    Neuronpedia

    INDEX
    Explanations

    Vehicle identification numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᅵ
    -0.08
    עם
    -0.07
    fullName
    -0.07
     enormous
    -0.07
    ----------↵↵
    -0.07
    公共资源
    -0.07
    嗝
    -0.07
     commerce
    -0.07
     paycheck
    -0.07
     Parkway
    -0.07
    POSITIVE LOGITS
    _include
    0.07
    ALS
    0.06
    โหล
    0.06
     photographers
    0.06
    amentos
    0.06
     lenders
    0.06
    фон
    0.06
    _bottom
    0.06
     اليمن
    0.06
    منتديات
    0.06
    Act Density 0.001%

    No Known Activations