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

    Neuronpedia

    INDEX
    Explanations

    permission

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     demora
    -0.08
     Salaam
    -0.08
     gil
    -0.07
    ivik
    -0.07
     Olympia
    -0.07
    263
    -0.07
     Mounted
    -0.07
    rest
    -0.07
     Falls
    -0.07
     funcionario
    -0.07
    POSITIVE LOGITS
     तय
    0.08
     toegang
    0.07
     अत्य
    0.07
     predefined
    0.07
     truy
    0.07
     مسب
    0.07
    barer
    0.07
     ಅತ್ಯ
    0.07
    kasten
    0.07
     மிகவும்
    0.07
    Act Density 0.002%

    No Known Activations