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

    Neuronpedia

    INDEX
    Explanations

    addClass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    请
    -0.07
    ቱ
    -0.07
    Gay
    -0.07
    同步
    -0.06
    输入
    -0.06
    utura
    -0.06
    ᨳ
    -0.06
    乙烯
    -0.06
    trand
    -0.06
    URE
    -0.06
    POSITIVE LOGITS
    ADX
    0.07
    뻘
    0.07
     .....
    0.07
     extra
    0.07
    ･･･
    0.07
    -sample
    0.07
    (answer
    0.07
    〠
    0.07
    泻
    0.07
    ㅑ
    0.07
    Act Density 0.001%

    No Known Activations