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

    Neuronpedia

    INDEX
    Explanations

    URLs and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gelen
    -0.06
     وز
    -0.06
    拼
    -0.06
    ------------------------------
    -0.06
    oğu
    -0.06
    HttpStatus
    -0.06
    								↵
    -0.06
    셜
    -0.06
                                 ↵
    -0.06
     atau
    -0.06
    POSITIVE LOGITS
     arbe
    0.07
     automat
    0.06
     orgasm
    0.06
    Nov
    0.06
    kHz
    0.06
    Kat
    0.06
     reactors
    0.06
    (日
    0.06
    ości
    0.06
     snork
    0.06
    Act Density 0.124%

    No Known Activations