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

    Neuronpedia

    INDEX
    Explanations

    Surveys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ansion
    -0.07
    Email
    -0.07
    Row
    -0.07
    ático
    -0.06
    ип
    -0.06
     EQUAL
    -0.06
     available
    -0.06
    '],↵↵
    -0.06
     voices
    -0.06
    itas
    -0.06
    POSITIVE LOGITS
     tanın
    0.07
     moderne
    0.07
     oranı
    0.07
    (helper
    0.06
     للإ
    0.06
    ([&
    0.06
    (EC
    0.06
    _articles
    0.06
     Sponsored
    0.06
     recipro
    0.06
    Act Density 0.019%

    No Known Activations