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

    Neuronpedia

    INDEX
    Explanations

    code and URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Libre
    -0.07
    ursos
    -0.07
    (frames
    -0.06
    Mining
    -0.06
    _IT
    -0.06
    RECT
    -0.06
     RTAL
    -0.06
    IllegalArgumentException
    -0.06
    leting
    -0.06
    557
    -0.06
    POSITIVE LOGITS
    (土
    0.07
     Settings
    0.06
     تاثیر
    0.06
     geniş
    0.06
     elegance
    0.06
     кот
    0.06
     backwards
    0.06
    increase
    0.06
     complicated
    0.06
     higher
    0.06
    Act Density 0.166%

    No Known Activations