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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    。この
    -0.07
    iez
    -0.06
    stem
    -0.06
    яс
    -0.06
     confisc
    -0.06
     С
    -0.06
    _scr
    -0.06
    líb
    -0.06
    .GetBytes
    -0.06
    .pres
    -0.05
    POSITIVE LOGITS
     pelvic
    0.08
    /Common
    0.07
     Ging
    0.07
    -none
    0.06
     Anatomy
    0.06
    मक
    0.06
     Posts
    0.06
     Mad
    0.06
     metaph
    0.06
    _DIFF
    0.06
    Act Density 0.253%

    No Known Activations