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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    neos
    -0.08
    جان
    -0.08
     क्ष
    -0.07
    து
    -0.07
     baš
    -0.07
     என்ன
    -0.07
     Fon
    -0.07
     Mosaic
    -0.07
     மெ
    -0.07
    ộn
    -0.07
    POSITIVE LOGITS
    icals
    0.09
    HP
    0.08
     HP
    0.08
     ASAP
    0.08
     sah
    0.08
     hp
    0.08
    .,
    0.08
     hrs
    0.07
    inct
    0.07
    iliation
    0.07
    Act Density 0.246%

    No Known Activations