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
     전화
    -0.06
     computing
    -0.06
     inund
    -0.06
    ATEG
    -0.06
     внут
    -0.06
     보내
    -0.06
     Casual
    -0.06
    났다
    -0.06
    หา
    -0.06
     THROUGH
    -0.06
    POSITIVE LOGITS
     amd
    0.07
     prick
    0.06
     Jap
    0.06
     ald
    0.06
    ‌ن
    0.06
     roy
    0.06
    кові
    0.06
     tweet
    0.06
    .get
    0.06
    ीएम
    0.06
    Act Density 0.001%

    No Known Activations