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

    Neuronpedia

    INDEX
    Explanations

    help

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    анси
    -0.07
    retry
    -0.07
     DPI
    -0.06
     rotary
    -0.06
     TTL
    -0.06
     каб
    -0.06
     weary
    -0.06
     segundos
    -0.06
    -cont
    -0.06
    severity
    -0.06
    POSITIVE LOGITS
     unle
    0.06
     phim
    0.06
     bapt
    0.06
     saç
    0.06
    拉
    0.06
    [cnt
    0.06
    poon
    0.06
    導
    0.06
     McL
    0.06
    quez
    0.06
    Act Density 0.019%

    No Known Activations