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

    Neuronpedia

    INDEX
    Explanations

    liability disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     лод
    -0.08
    ப்படுகிறது
    -0.08
     Julius
    -0.08
     Column
    -0.08
    ూమ
    -0.08
     Zodiac
    -0.08
    umed
    -0.08
     zodiac
    -0.08
     ול
    -0.07
    oterapia
    -0.07
    POSITIVE LOGITS
     daños
    0.10
     CONSEQUENTIAL
    0.09
    .Errorf
    0.09
    دع
    0.09
     consequ
    0.08
     damages
    0.08
     consect
    0.08
     INCIDENTAL
    0.08
    损
    0.08
    費
    0.08
    Act Density 0.002%

    No Known Activations