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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    盛世
    -0.07
    Professor
    -0.07
     selv
    -0.07
    baseline
    -0.07
    seg
    -0.07
     diferença
    -0.07
    持有
    -0.07
    @Data
    -0.07
     newSize
    -0.07
    TK
    -0.06
    POSITIVE LOGITS
     Greenville
    0.07
     Yorkshire
    0.07
    鬯
    0.06
    דעות
    0.06
    兖
    0.06
     Bryant
    0.06
    .ProgressBar
    0.06
     graphics
    0.06
    花钱
    0.06
    UnityEngine
    0.06
    Act Density 0.000%

    No Known Activations