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

    Neuronpedia

    INDEX
    Explanations

    general text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("-");↵
    -0.07
    ců
    -0.07
    ])(
    -0.06
    آخر
    -0.06
     fr
    -0.06
    美國
    -0.06
     DbType
    -0.06
    +")
    -0.06
    (木
    -0.06
     SHA
    -0.06
    POSITIVE LOGITS
    _Address
    0.06
     ifs
    0.06
    κα
    0.06
     judging
    0.06
     conveniently
    0.06
    pread
    0.06
     Appears
    0.06
     باشگاه
    0.06
     efficiencies
    0.06
     конс
    0.06
    Act Density 0.006%

    No Known Activations