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

    Neuronpedia

    INDEX
    Explanations

    Question/post instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     homeowner
    -0.08
    豪
    -0.07
     rank
    -0.07
    從
    -0.07
     morning
    -0.07
    按时
    -0.07
    drivers
    -0.07
    -run
    -0.07
     distribution
    -0.07
    law
    -0.07
    POSITIVE LOGITS
    蒎
    0.08
    os
    0.07
    眍
    0.06
    娆
    0.06
    鼙
    0.06
     Erotische
    0.06
    깓
    0.06
    _false
    0.06
     Eph
    0.06
    튿
    0.06
    Act Density 0.124%

    No Known Activations