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

    Neuronpedia

    INDEX
    Explanations

    utf

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sagen
    -0.07
     sophistic
    -0.06
    我们
    -0.06
     Nice
    -0.06
     Rouge
    -0.06
     فار
    -0.06
    IfNeeded
    -0.06
    jectives
    -0.06
     output
    -0.06
    ouve
    -0.06
    POSITIVE LOGITS
    jeta
    0.06
    _View
    0.06
     except
    0.06
    .Card
    0.06
    _banner
    0.06
    _barrier
    0.06
    ตร
    0.06
    (count
    0.06
    partials
    0.06
    elog
    0.06
    Act Density 0.001%

    No Known Activations