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
    grunt
    -0.07
    __("
    -0.07
     chuyến
    -0.06
    bian
    -0.06
    _crossentropy
    -0.06
    充
    -0.06
     otel
    -0.06
    (yy
    -0.06
    _nav
    -0.06
    _blocked
    -0.06
    POSITIVE LOGITS
    _upload
    0.07
     pontos
    0.07
     различных
    0.07
    ('.',
    0.06
    _G
    0.06
    _px
    0.06
    _temp
    0.06
    _Record
    0.06
    argument
    0.06
    Middle
    0.06
    Act Density 0.055%

    No Known Activations