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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elde
    -0.07
     ingen
    -0.06
     فرزند
    -0.06
     müzik
    -0.06
     국내
    -0.06
     neighbours
    -0.06
    顔を
    -0.06
    대행
    -0.06
    ピ
    -0.06
     ün
    -0.06
    POSITIVE LOGITS
     خواه
    0.07
     Cartoon
    0.07
    loid
    0.07
     Needed
    0.07
     underestimate
    0.07
    ki
    0.06
    ницы
    0.06
     glimpse
    0.06
    .Visibility
    0.06
    FILE
    0.06
    Act Density 0.129%

    No Known Activations