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

    Neuronpedia

    INDEX
    Explanations

    regex

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shaded
    -0.09
    polygon
    -0.08
     casserole
    -0.08
    남
    -0.08
    aderas
    -0.08
     solares
    -0.08
     Cooper
    -0.08
     trolley
    -0.08
     hemisphere
    -0.08
     fich
    -0.07
    POSITIVE LOGITS
     Regex
    0.18
     regex
    0.17
    regex
    0.17
    .Regex
    0.17
    (regex
    0.16
    Regex
    0.16
    _regex
    0.16
    _REGEX
    0.16
    .regex
    0.15
    regexp
    0.13
    Act Density 0.010%

    No Known Activations