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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    早点
    -0.07
     informing
    -0.07
    不同程度
    -0.07
     sor
    -0.06
    耙
    -0.06
    ◼
    -0.06
    些
    -0.06
     Buf
    -0.06
     pieces
    -0.06
     Hint
    -0.06
    POSITIVE LOGITS
    安娜
    0.07
     Att
    0.07
    rena
    0.06
     bluetooth
    0.06
     fluor
    0.06
    ouro
    0.06
    冲击
    0.06
    ()))
    0.06
     Pra
    0.06
    鸡
    0.06
    Act Density 0.014%

    No Known Activations