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

    Neuronpedia

    INDEX
    Explanations

    way

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     هاي
    -0.07
     官
    -0.07
     hayata
    -0.07
     표시
    -0.07
    echa
    -0.07
    avicon
    -0.06
     सर
    -0.06
     newspaper
    -0.06
    imestone
    -0.06
    okus
    -0.06
    POSITIVE LOGITS
    abh
    0.06
     posto
    0.06
    Blob
    0.06
    (parse
    0.06
     grip
    0.06
    *&
    0.06
     pygame
    0.05
     alcohol
    0.05
     SAFE
    0.05
     vw
    0.05
    Act Density 0.002%

    No Known Activations