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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🐪
    -0.07
     CHECK
    -0.07
     attention
    -0.06
    .SplitContainer
    -0.06
    팅
    -0.06
    佛山市
    -0.06
    .VideoCapture
    -0.06
    欣赏
    -0.06
    믑
    -0.06
    将近
    -0.06
    POSITIVE LOGITS
    之力
    0.07
     Reserve
    0.07
     DISPLAY
    0.07
     resale
    0.07
     sister
    0.07
    キャラ
    0.07
    ƪ
    0.07
    쪗
    0.06
    Boundary
    0.06
    hec
    0.06
    Act Density 0.000%

    No Known Activations