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

    Neuronpedia

    INDEX
    Explanations

    S

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .AP
    -0.07
    ith
    -0.06
     ecstatic
    -0.06
     captivity
    -0.06
     tímto
    -0.06
    orne
    -0.06
     Azerbaijan
    -0.06
    052
    -0.06
     cata
    -0.06
     glaciers
    -0.06
    POSITIVE LOGITS
    ‌های
    0.06
     Tucker
    0.06
    477
    0.06
     Select
    0.06
     هفته
    0.06
     발표
    0.06
    LN
    0.06
     tries
    0.06
     common
    0.06
    branch
    0.06
    Act Density 0.000%

    No Known Activations