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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Off
    -0.07
     Hilton
    -0.07
    DFS
    -0.07
     preseason
    -0.06
     Gol
    -0.06
     oslo
    -0.06
     DISTRIBUT
    -0.06
     premiere
    -0.06
    BeginInit
    -0.06
     REV
    -0.06
    POSITIVE LOGITS
    Soap
    0.07
    监
    0.07
     ayrıntı
    0.06
    placement
    0.06
    亿
    0.06
    (nullable
    0.06
    医疗
    0.06
    一页
    0.06
    ONO
    0.06
    ify
    0.06
    Act Density 0.034%

    No Known Activations