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

    Neuronpedia

    INDEX
    Explanations

    patent numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ograd
    -0.07
    �
    -0.07
    <Component
    -0.07
     nộ
    -0.07
     contro
    -0.06
    �
    -0.06
    _digits
    -0.06
    hog
    -0.06
    amsung
    -0.06
    amics
    -0.06
    POSITIVE LOGITS
     classifications
    0.07
    陕
    0.07
     //(
    0.07
    แหละ
    0.07
    成都市
    0.07
     Bran
    0.07
    leccion
    0.07
    "is
    0.07
    _station
    0.07
     Localization
    0.07
    Act Density 0.001%

    No Known Activations