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

    Neuronpedia

    INDEX
    Explanations

    Code-related symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    example
    -0.08
    erni
    -0.07
    (Collection
    -0.07
     construcción
    -0.07
    欢迎
    -0.07
    (settings
    -0.07
    (Material
    -0.07
    icular
    -0.07
     suces
    -0.07
     converts
    -0.07
    POSITIVE LOGITS
    なし
    0.09
     بطريقة
    0.08
     નહિ
    0.08
     provoc
    0.08
     yd
    0.08
     juist
    0.08
     evas
    0.08
     lowu
    0.08
     жоқ
    0.08
     edt
    0.08
    Act Density 0.099%

    No Known Activations