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

    Neuronpedia

    INDEX
    Explanations

    variable substitution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    herr
    -0.09
     Uso
    -0.08
    ಗ್ಗೆ
    -0.08
     Эти
    -0.08
    告诉
    -0.08
     hjäl
    -0.08
     uso
    -0.08
     meyd
    -0.08
    mond
    -0.08
     servidores
    -0.08
    POSITIVE LOGITS
    [t
    0.09
    0.08
     replaced
    0.08
    [i
    0.08
    [len
    0.08
    setting
    0.08
    .↵↵
    0.08
     setting
    0.07
    [
    0.07
    (t
    0.07
    Act Density 0.062%
    No Known Activations