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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بأ
    -0.07
    acf
    -0.07
    ProgressHUD
    -0.07
     downstream
    -0.07
    ク
    -0.07
     colspan
    -0.07
     الشم
    -0.06
    ovně
    -0.06
    ColorBrush
    -0.06
     дви
    -0.06
    POSITIVE LOGITS
     burg
    0.06
     lease
    0.06
     republic
    0.06
     birds
    0.06
     Bill
    0.06
    Edward
    0.06
     Ven
    0.06
     Ministers
    0.06
     Michele
    0.06
    (cfg
    0.06
    Act Density 0.000%

    No Known Activations