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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'https
    -0.07
    sou
    -0.07
     kwargs
    -0.07
    _sess
    -0.06
    別
    -0.06
     projector
    -0.06
     realization
    -0.06
    -art
    -0.06
     newsletters
    -0.06
     Baz
    -0.06
    POSITIVE LOGITS
    \Module
    0.06
    (API
    0.06
     Georgetown
    0.06
     nightclub
    0.06
    交通
    0.06
    omedical
    0.06
     FRE
    0.06
    atoria
    0.06
     Retrieves
    0.06
    eee
    0.06
    Act Density 0.002%

    No Known Activations