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

    Neuronpedia

    INDEX
    Explanations

    Journal articles/supplements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,W
    -0.06
    波
    -0.06
     detox
    -0.06
     dále
    -0.06
    _black
    -0.06
    .Variable
    -0.06
     BEST
    -0.06
    BP
    -0.06
    تح
    -0.06
    福
    -0.06
    POSITIVE LOGITS
    _sun
    0.07
     heavily
    0.07
     jugar
    0.06
    Compatibility
    0.06
    forcer
    0.06
    izzlies
    0.06
     chờ
    0.06
    heavy
    0.06
    坐在
    0.06
     prestige
    0.06
    Act Density 0.151%

    No Known Activations