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

    Neuronpedia

    INDEX
    Explanations

    China locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    217
    -0.07
     sequ
    -0.06
    (d
    -0.06
     anno
    -0.06
     Suddenly
    -0.06
     clockwise
    -0.06
     facts
    -0.06
     overridden
    -0.06
    930
    -0.06
     inventive
    -0.06
    POSITIVE LOGITS
    ="<<
    0.07
    ]?
    0.07
    »)
    0.06
    jury
    0.06
    »,
    0.06
    _probability
    0.06
    -blind
    0.06
    veal
    0.06
    ..:
    0.06
    MC
    0.06
    Act Density 0.003%

    No Known Activations