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

    Neuronpedia

    INDEX
    Explanations

    Parentheses and shape

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Warsaw
    -0.08
    Driving
    -0.08
     Driving
    -0.08
     driving
    -0.08
    /git
    -0.08
    ೋ
    -0.08
     поверх
    -0.07
    浦
    -0.07
     केन्द्र
    -0.07
    -driving
    -0.07
    POSITIVE LOGITS
     Specifies
    0.08
     Defines
    0.08
    Hin
    0.08
     specifies
    0.08
    0.08
    CGSize
    0.08
    ungal
    0.08
    指定
    0.08
     مشخص
    0.08
     Hin
    0.07
    Act Density 0.004%
    No Known Activations