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

    Neuronpedia

    INDEX
    Explanations

    treat others

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     적
    -0.07
    金牌
    -0.07
     decor
    -0.07
     ctr
    -0.07
     стр
    -0.07
    읿
    -0.06
    專
    -0.06
    咍
    -0.06
    fillType
    -0.06
    工匠
    -0.06
    POSITIVE LOGITS
    稿件
    0.07
     cauliflower
    0.07
    0.07
     stayed
    0.07
    example
    0.07
    のある
    0.07
    aju
    0.07
     BOARD
    0.07
    AJ
    0.07
    aleb
    0.07
    Act Density 0.012%

    No Known Activations