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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Раз
    -0.07
     Một
    -0.07
     Procedures
    -0.07
    312
    -0.07
     Reconstruction
    -0.06
    ох
    -0.06
    riad
    -0.06
    (Throwable
    -0.06
    년
    -0.06
    unable
    -0.06
    POSITIVE LOGITS
    !'↵
    0.09
    !↵
    0.08
    ै?↵
    0.08
    ें↵
    0.08
    »↵
    0.08
    !!!↵
    0.08
    .”↵
    0.08
    ें।↵
    0.08
    !↵
    0.08
    ／↵
    0.08
    Act Density 0.039%

    No Known Activations