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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Surface
    -0.07
    吧
    -0.07
    curities
    -0.07
    财
    -0.07
     Ка
    -0.07
     这
    -0.06
    Hash
    -0.06
    ."↵
    -0.06
    Sr
    -0.06
    ६
    -0.06
    POSITIVE LOGITS
     Wonderful
    0.08
    _good
    0.07
     inflater
    0.07
     повідом
    0.06
    pellier
    0.06
     besteht
    0.06
    ILLISECONDS
    0.06
    choice
    0.06
     당신
    0.06
     правильно
    0.06
    Act Density 0.002%

    No Known Activations