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

    Neuronpedia

    INDEX
    Explanations

    direction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oklyn
    -0.08
     usleep
    -0.07
    mö
    -0.07
    _traffic
    -0.07
    ',[
    -0.07
    ughter
    -0.07
    ollo
    -0.07
    .sync
    -0.06
     gli
    -0.06
    楼市
    -0.06
    POSITIVE LOGITS
    fraction
    0.08
     excellent
    0.07
     RIGHT
    0.07
    .cross
    0.07
    виз
    0.07
    儆
    0.07
     המקורי
    0.07
    flags
    0.06
    _ValueChanged
    0.06
    즙
    0.06
    Act Density 0.004%

    No Known Activations