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

    Neuronpedia

    INDEX
    Explanations

    possible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Microsoft
    -0.07
    Mix
    -0.07
    тов
    -0.06
    _survey
    -0.06
     satu
    -0.06
    _level
    -0.06
    civil
    -0.06
    :semicolon
    -0.06
    Study
    -0.06
    ervices
    -0.06
    POSITIVE LOGITS
    지만
    0.07
    кової
    0.06
     quick
    0.06
    _SSL
    0.06
    (bs
    0.06
     ubyt
    0.06
     DatePicker
    0.06
    держ
    0.06
    _RESET
    0.06
     ESPN
    0.06
    Act Density 0.104%

    No Known Activations