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
    -provider
    -0.07
    detector
    -0.06
    percent
    -0.06
     Wiki
    -0.06
     orm
    -0.06
    تماد
    -0.06
     Governor
    -0.06
     önüne
    -0.06
     homage
    -0.06
    Football
    -0.05
    POSITIVE LOGITS
    .pi
    0.07
     Alt
    0.07
     důvod
    0.07
    _CLASSES
    0.06
    (master
    0.06
    (td
    0.06
     palp
    0.06
    Algorithm
    0.06
    Pen
    0.06
     ов
    0.06
    Act Density 0.004%

    No Known Activations