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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .MediaType
    -0.07
     düzenlen
    -0.07
    .BorderColor
    -0.07
    😒
    -0.07
    ublished
    -0.07
    呇
    -0.06
    发布公告
    -0.06
    漲
    -0.06
     😉
    -0.06
    Ҁ
    -0.06
    POSITIVE LOGITS
     supreme
    0.08
    叔叔
    0.08
    قا
    0.08
    也需要
    0.07
    setattr
    0.07
    elementType
    0.07
    whereIn
    0.07
    	handler
    0.07
    √
    0.07
    锤
    0.07
    Act Density 0.054%

    No Known Activations