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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     docket
    -0.09
     okut
    -0.08
    hep
    -0.08
    APA
    -0.08
     Pain
    -0.08
     boven
    -0.08
     บ
    -0.08
     Salaam
    -0.08
     سوق
    -0.07
     oner
    -0.07
    POSITIVE LOGITS
    长度
    0.16
     vowels
    0.14
    字符串
    0.14
     substring
    0.13
    .substring
    0.13
    substring
    0.13
    Substring
    0.13
     дли
    0.13
    Length
    0.13
    _length
    0.13
    Act Density 0.027%

    No Known Activations