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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    更改
    -0.07
     corro
    -0.07
    configs
    -0.07
     amph
    -0.06
    ≤
    -0.06
    隻
    -0.06
    .Patient
    -0.06
     optim
    -0.06
     Đi
    -0.06
    奭
    -0.06
    POSITIVE LOGITS
    DetailView
    0.08
    Wait
    0.07
     invalidate
    0.07
     Displays
    0.07
    なか
    0.07
     Knock
    0.07
     Golden
    0.07
     khoảng
    0.07
    货架
    0.07
    あ
    0.07
    Act Density 0.148%

    No Known Activations