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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shoulders
    -0.08
     scratched
    -0.08
    —or
    -0.08
     Abroad
    -0.08
    Здравствуйте
    -0.07
     //--------------------------------
    -0.07
     gefällt
    -0.07
     قد
    -0.07
     وال
    -0.07
     Saúde
    -0.07
    POSITIVE LOGITS
    filename
    0.09
     dát
    0.08
    usually
    0.07
    reasonable
    0.07
     inde
    0.07
     tež
    0.07
     الشي
    0.07
     repetitive
    0.07
    Ind
    0.07
     बाज
    0.07
    Act Density 0.018%

    No Known Activations