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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    В
    -0.07
    Њ
    -0.07
    差
    -0.07
    ῥ
    -0.07
    发行
    -0.07
     adverse
    -0.06
    [item
    -0.06
    ᠰ
    -0.06
     tension
    -0.06
    rase
    -0.06
    POSITIVE LOGITS
     Nhưng
    0.07
    想过
    0.07
    "},↵
    0.07
    0.07
    ())),↵
    0.07
    していない
    0.07
    אור
    0.07
    보고
    0.07
     불구하고
    0.07
     Axios
    0.07
    Act Density 0.290%

    No Known Activations