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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Parkinson
    -0.07
    <count
    -0.07
     TYPO
    -0.06
    atinum
    -0.06
     없다
    -0.06
    HOW
    -0.06
    attle
    -0.06
     listopadu
    -0.06
     Berk
    -0.06
     Salah
    -0.06
    POSITIVE LOGITS
     installations
    0.07
    ...↵
    0.07
    �
    0.06
     '}';↵
    0.06
    _hist
    0.06
     "";↵
    0.06
    ,...↵↵
    0.06
    \\
    0.06
    _voltage
    0.06
     [-
    0.06
    Act Density 0.021%

    No Known Activations