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

    Neuronpedia

    INDEX
    Explanations

    Code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exceeding
    -0.07
    mysql
    -0.07
     ers
    -0.06
    (StringUtils
    -0.06
    mutex
    -0.06
    что
    -0.06
     quand
    -0.06
     athletes
    -0.06
     Chin
    -0.06
    凌
    -0.06
    POSITIVE LOGITS
    .tar
    0.07
     وابسته
    0.06
    sah
    0.06
     adapting
    0.06
    味
    0.06
     UserInfo
    0.06
    HandlerContext
    0.06
    ША
    0.06
     mír
    0.06
    -fixed
    0.06
    Act Density 0.056%

    No Known Activations