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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gaul
    -0.08
    春风
    -0.07
    _validation
    -0.07
     tuples
    -0.07
     Enterprises
    -0.07
    Green
    -0.07
    趋于
    -0.07
     plead
    -0.07
     evolves
    -0.07
     communion
    -0.07
    POSITIVE LOGITS
    ?,↵
    0.07
    lington
    0.07
     iht
    0.07
    ']).
    0.07
    wart
    0.07
    .toObject
    0.07
     ^
    0.07
    ;};↵
    0.07
    bild
    0.07
    IFICATIONS
    0.07
    Act Density 0.003%

    No Known Activations