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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    โรงแ
    -0.07
     enjoyable
    -0.07
    _has
    -0.06
     Geschichte
    -0.06
    之夜
    -0.06
    漳州
    -0.06
    顺序
    -0.06
     Después
    -0.06
    weekly
    -0.06
    提名
    -0.06
    POSITIVE LOGITS
    摘要
    0.08
    Singapore
    0.07
    Qi
    0.07
    قول
    0.07
     Boise
    0.06
    'i
    0.06
    Disallow
    0.06
     เพราะ
    0.06
    ù
    0.06
     tac
    0.06
    Act Density 0.027%

    No Known Activations