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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks/parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _EDITOR
    -0.06
     پیچ
    -0.06
     biện
    -0.06
     arrogant
    -0.06
    .IndexOf
    -0.06
     Fried
    -0.06
    แฟ
    -0.06
     ένας
    -0.06
     Sleeve
    -0.06
     Rajasthan
    -0.06
    POSITIVE LOGITS
    Follow
    0.08
     […]
    0.07
    185
    0.07
    —↵↵
    0.07
     tenure
    0.07
    _experiment
    0.07
    (driver
    0.06
    _bar
    0.06
    295
    0.06
    ζε
    0.06
    Act Density 0.341%

    No Known Activations