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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     briefly
    -0.07
    (cmp
    -0.07
    hetto
    -0.07
    4
    -0.06
    Taylor
    -0.06
    (h
    -0.06
    _design
    -0.06
    uno
    -0.06
    fh
    -0.06
    libft
    -0.06
    POSITIVE LOGITS
    .Compile
    0.07
     për
    0.06
     als
    0.06
     ///</
    0.06
     cuando
    0.06
    stay
    0.06
     vielen
    0.06
     менше
    0.06
     �
    0.06
     meng
    0.06
    Act Density 0.043%

    No Known Activations