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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    特色
    -0.07
     GetUser
    -0.07
    369
    -0.06
    活動
    -0.06
    狀
    -0.06
    тися
    -0.06
    acher
    -0.06
    calling
    -0.06
    GameManager
    -0.06
     subscriber
    -0.06
    POSITIVE LOGITS
     ninh
    0.07
    .visibility
    0.06
    utom
    0.06
     شکست
    0.06
     discontinued
    0.06
    fake
    0.06
     Hind
    0.06
    -war
    0.06
    jury
    0.06
    indy
    0.06
    Act Density 0.015%

    No Known Activations