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

    Neuronpedia

    INDEX
    Explanations

    decorators and annotations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    @",
    1.04
     "@
    0.99
    @
    0.97
     "@{
    0.96
     spurious
    0.95
     `@
    0.91
    ("@
    0.87
     @
    0.87
    軧
    0.85
    면서
    0.82
    POSITIVE LOGITS
    staticmethod
    1.41
    SuppressWarnings
    1.09
    classmethod
    1.00
    Override
    0.98
    jsonwebtoken
    0.93
    csrf
    0.92
    Deprecated
    0.90
    hotmail
    0.87
    พัก
    0.84
    PCA
    0.83
    Act Density 0.008%

    No Known Activations