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

    Neuronpedia

    INDEX
    Explanations

    quotations/extractions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hand
    -0.06
    طلق
    -0.06
     sert
    -0.06
     Km
    -0.06
     designated
    -0.06
    -parent
    -0.06
    _bit
    -0.06
     sounded
    -0.06
     groom
    -0.06
    gebn
    -0.06
    POSITIVE LOGITS
    .chdir
    0.06
    Shares
    0.06
    gons
    0.06
     пример
    0.06
    charge
    0.06
     Sed
    0.06
    Inverse
    0.06
    .Categories
    0.06
     twists
    0.06
     timedelta
    0.06
    Act Density 0.289%

    No Known Activations