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

    Neuronpedia

    INDEX
    Explanations

    group

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    り
    -0.07
    .opts
    -0.06
    PBS
    -0.06
     Tato
    -0.06
    apo
    -0.06
     beg
    -0.06
     tbl
    -0.06
    اشت
    -0.06
     spi
    -0.06
    632
    -0.06
    POSITIVE LOGITS
     @@↵
    0.06
     savvy
    0.06
    !!!!!
    0.06
     objetos
    0.06
    265
    0.06
     Fasc
    0.06
     перев
    0.06
     concerned
    0.06
    !!↵↵
    0.06
     Essential
    0.06
    Act Density 0.004%

    No Known Activations