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

    Neuronpedia

    INDEX
    Explanations

    history API and hash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thick
    -0.08
     mesmo
    -0.07
     discipline
    -0.07
    边界
    -0.07
    摧
    -0.07
    贷
    -0.07
    态势
    -0.07
     magnitude
    -0.07
     Mol
    -0.07
     pare
    -0.07
    POSITIVE LOGITS
    쁨
    0.07
     analsex
    0.07
    后悔
    0.07
    ajax
    0.07
    雪花
    0.07
    edback
    0.07
    ﹷ
    0.07
    ↞
    0.07
    <hr
    0.07
    🔀
    0.06
    Act Density 0.011%

    No Known Activations