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

    Neuronpedia

    INDEX
    Explanations

    regular expressions, parsing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aderas
    -0.09
    �
    -0.08
     honored
    -0.08
    үүн
    -0.08
     genannt
    -0.07
     Сен
    -0.07
    irit
    -0.07
     Alicia
    -0.07
    梯
    -0.07
    dda
    -0.07
    POSITIVE LOGITS
     regex
    0.17
     Regex
    0.17
    regex
    0.16
    Regex
    0.16
    _REGEX
    0.16
    _regex
    0.15
    (regex
    0.15
    .Regex
    0.14
    .regex
    0.13
    regexp
    0.13
    Act Density 0.018%

    No Known Activations