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

    Neuronpedia

    INDEX
    Explanations

    Comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    素材
    -0.07
    深处
    -0.07
     autoComplete
    -0.07
     MatTable
    -0.07
     Erotik
    -0.07
    _rsa
    -0.06
    CharCode
    -0.06
    pNet
    -0.06
     OK
    -0.06
    畋
    -0.06
    POSITIVE LOGITS
    lood
    0.07
     Rohing
    0.07
     removal
    0.07
    '=>$
    0.06
     '=',
    0.06
    בלעדי
    0.06
     الملك
    0.06
    _travel
    0.06
    其实是
    0.06
     Imperial
    0.06
    Act Density 0.029%

    No Known Activations