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

    Neuronpedia

    INDEX
    Explanations

    Attribution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     extractor
    -0.08
     manga
    -0.07
    .dup
    -0.06
     заб
    -0.06
     finished
    -0.06
     concessions
    -0.06
    Daily
    -0.06
     UCS
    -0.06
     PAD
    -0.06
    (Screen
    -0.06
    POSITIVE LOGITS
    いや
    0.07
     půj
    0.06
    _references
    0.06
     Peanut
    0.06
    (API
    0.06
    ／:
    0.06
     истории
    0.06
    �
    0.06
    عد
    0.06
     persu
    0.05
    Act Density 0.002%

    No Known Activations