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

    Neuronpedia

    INDEX
    Explanations

    complacency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ndo
    -0.07
    Reward
    -0.07
     kunt
    -0.07
    推介
    -0.07
    ũ
    -0.07
    eding
    -0.07
    יכ
    -0.07
    -hand
    -0.07
    庚
    -0.07
    疑
    -0.07
    POSITIVE LOGITS
    dataset
    0.07
    .MapPath
    0.07
     
    0.07
    MU
    0.06
    #endregion
    0.06
    𝖘
    0.06
     Mult
    0.06
    abcd
    0.06
    ناس
    0.06
    满
    0.06
    Act Density 0.001%

    No Known Activations