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

    Neuronpedia

    INDEX
    Explanations

    semicolon and quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     സ്ത്രീ
    -0.08
    Texts
    -0.08
    Alg
    -0.08
     Pessoas
    -0.08
     Alg
    -0.08
     കുട്ട
    -0.08
    _digit
    -0.08
     persoonsgegevens
    -0.07
     കുഞ്ഞ
    -0.07
     digne
    -0.07
    POSITIVE LOGITS
     nodig
    0.08
    (offset
    0.08
     sini
    0.08
     ub
    0.08
    fatt
    0.08
    ：中国
    0.07
     validates
    0.07
     China
    0.07
     dsp
    0.07
     tall
    0.07
    Act Density 0.001%

    No Known Activations