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

    Neuronpedia

    INDEX
    Explanations

    is/of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    スレ
    -0.07
    민
    -0.07
     theo
    -0.07
     CONSTANT
    -0.06
     Chí
    -0.06
     eing
    -0.06
     Shelter
    -0.06
     달
    -0.06
     тут
    -0.06
     thuốc
    -0.06
    POSITIVE LOGITS
    ر
    0.06
    (interface
    0.06
    )d
    0.06
     kvinnor
    0.06
    grams
    0.06
     پوست
    0.06
    Review
    0.06
     silence
    0.06
    =False
    0.06
     firms
    0.06
    Act Density 0.004%

    No Known Activations