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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (candidate
    -0.07
    ограм
    -0.07
    arrison
    -0.07
     کمتر
    -0.07
     credential
    -0.07
     kaynak
    -0.07
     واقعی
    -0.07
     mocks
    -0.07
    <Model
    -0.07
    _normal
    -0.07
    POSITIVE LOGITS
     veterin
    0.06
    ."),↵
    0.06
     تاب
    0.06
    UTF
    0.06
     chlor
    0.06
     tex
    0.06
     valueType
    0.06
     cv
    0.06
    HORT
    0.06
     "../../../../
    0.06
    Act Density 0.156%

    No Known Activations