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

    Neuronpedia

    INDEX
    Explanations

    2 or 3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    м
    -0.06
     cavern
    -0.06
    elm
    -0.06
     frustrations
    -0.06
     charitable
    -0.06
     sû
    -0.06
    ertura
    -0.06
     Don
    -0.06
     reads
    -0.06
    erm
    -0.06
    POSITIVE LOGITS
    Kevin
    0.07
    .Argument
    0.07
    .Alpha
    0.07
     способ
    0.06
    .mult
    0.06
     cudaMemcpy
    0.06
     біля
    0.06
    .Stdout
    0.06
    {},↵
    0.06
    تبار
    0.06
    Act Density 0.020%

    No Known Activations