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

    Neuronpedia

    INDEX
    Explanations

    laws/rules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    歌舞
    -0.07
    ゔ
    -0.07
    一阵
    -0.06
     dosage
    -0.06
    boo
    -0.06
    iates
    -0.06
    =./
    -0.06
    三项
    -0.06
    려
    -0.06
    業務
    -0.06
    POSITIVE LOGITS
     Predictor
    0.07
    中华人民
    0.07
    叟
    0.07
    icao
    0.07
     cere
    0.07
     whiteColor
    0.07
    stor
    0.07
     DATA
    0.07
     invaders
    0.07
    contributors
    0.06
    Act Density 0.039%

    No Known Activations