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

    Neuronpedia

    INDEX
    Explanations

    header files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ifikace
    -0.07
     nowrap
    -0.06
    _login
    -0.06
    ashing
    -0.06
    would
    -0.06
    '))
    -0.06
    _LOC
    -0.06
    (exports
    -0.06
    ')))
    -0.06
    、お
    -0.06
    POSITIVE LOGITS
    σον
    0.08
     тиж
    0.07
    OUNDS
    0.07
     population
    0.06
    етерб
    0.06
    号
    0.06
    ποτε
    0.06
     Isabel
    0.06
     αστ
    0.06
    ắp
    0.06
    Act Density 0.056%

    No Known Activations