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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     müşteri
    -0.06
     Lisp
    -0.06
    .JSONException
    -0.06
    (".")
    -0.06
    aed
    -0.06
     Sequ
    -0.06
     stead
    -0.06
    ंर
    -0.06
    Regular
    -0.06
     bedtime
    -0.05
    POSITIVE LOGITS
    (plugin
    0.07
     otur
    0.07
     такое
    0.07
    .removeChild
    0.06
    .*,
    0.06
    ience
    0.06
    Though
    0.06
    riminator
    0.06
     karıştır
    0.06
    ｢
    0.06
    Act Density 0.037%

    No Known Activations