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

    Neuronpedia

    INDEX
    Explanations

    threat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    жÑĥ
    -0.28
    inus
    -0.27
    奴
    -0.26
    หมวà¸Ķ
    -0.25
    ä¸Ńåħ±
    -0.25
    梦幻
    -0.25
    orton
    -0.24
    è¿Ļ个ä¸ĸçķĮ
    -0.24
    交éĢļå®īåħ¨
    -0.24
    lichkeit
    -0.24
    POSITIVE LOGITS
    iskey
    0.32
     opi
    0.27
    _supply
    0.26
     amnesty
    0.25
    oxide
    0.25
    ox
    0.24
     supply
    0.24
    ulan
    0.24
    upply
    0.24
    æ¿Ģç´ł
    0.24
    Act Density 0.784%

    No Known Activations