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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    И
    -0.07
    zdy
    -0.07
    Ж
    -0.07
    _except
    -0.06
    AINS
    -0.06
    如
    -0.06
    用于
    -0.06
    .getInstance
    -0.06
    <data
    -0.06
    jenis
    -0.06
    POSITIVE LOGITS
     scho
    0.07
     далеко
    0.07
     �
    0.07
     ред
    0.06
    .ISupportInitialize
    0.06
    .drawer
    0.06
     Dod
    0.06
     cran
    0.06
     Gren
    0.06
    .gallery
    0.06
    Act Density 0.006%

    No Known Activations