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

    Neuronpedia

    INDEX
    Explanations

    replacing words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pessoas
    -0.07
    Emoji
    -0.06
     xấu
    -0.06
     honey
    -0.06
     denn
    -0.06
    -0.06
     subsid
    -0.06
     WEEK
    -0.06
     destek
    -0.06
     eclectic
    -0.06
    POSITIVE LOGITS
    .arm
    0.07
    .В
    0.06
    (hdc
    0.06
     airs
    0.06
    [layer
    0.06
     emiss
    0.06
     nejvyšší
    0.06
    Chip
    0.06
     teg
    0.06
     Walt
    0.06
    Act Density 0.013%

    No Known Activations