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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    damn
    -0.07
    978
    -0.07
     وك
    -0.07
    筆
    -0.06
    ۱۶
    -0.06
     reckon
    -0.06
    續
    -0.06
     Dar
    -0.06
    劉
    -0.06
    BUR
    -0.06
    POSITIVE LOGITS
    Around
    0.07
    gnore
    0.07
    enheim
    0.07
    ASURE
    0.07
    .UserInfo
    0.06
    ταν
    0.06
    cmc
    0.06
    词
    0.06
    oblins
    0.06
     danych
    0.06
    Act Density 0.000%

    No Known Activations