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

    Neuronpedia

    INDEX
    Explanations

    ducible/reducible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :index
    -0.09
     dès
    -0.07
    .tv
    -0.07
    .work
    -0.06
     Guide
    -0.06
     avid
    -0.06
    tractive
    -0.06
    NSError
    -0.06
    ﻜ
    -0.06
    透视
    -0.06
    POSITIVE LOGITS
     SSH
    0.08
     virus
    0.07
     installation
    0.07
    styles
    0.07
    _UTIL
    0.07
    学校
    0.07
    компон
    0.07
    Communic
    0.07
     Concat
    0.07
     Prevention
    0.07
    Act Density 0.004%

    No Known Activations