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

    Neuronpedia

    INDEX
    Explanations

    back

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     percentile
    -0.08
     grupos
    -0.08
     Sarajevo
    -0.08
     groups
    -0.08
     interiors
    -0.08
     Dictionary
    -0.08
     artesanal
    -0.08
    群
    -0.08
     groepen
    -0.08
     affordable
    -0.08
    POSITIVE LOGITS
    reverse
    0.10
     inappropriate
    0.10
    _reverse
    0.10
     inadvert
    0.09
     reversed
    0.09
     unwanted
    0.09
     reverse
    0.09
    逆
    0.09
     उल
    0.08
     undue
    0.08
    Act Density 0.004%

    No Known Activations