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

    Neuronpedia

    INDEX
    Explanations

    society association

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Marvel
    -0.08
    毫升
    -0.07
    .gray
    -0.07
    ქ
    -0.07
     ян
    -0.07
    مب
    -0.06
    .AC
    -0.06
    roduced
    -0.06
    .maps
    -0.06
     sep
    -0.06
    POSITIVE LOGITS
    "});↵
    0.08
    感受到
    0.08
     NOTIFY
    0.08
     становится
    0.07
    成效
    0.07
    (ft
    0.07
     misery
    0.07
    .Local
    0.07
    澄清
    0.07
    _member
    0.07
    Act Density 0.012%

    No Known Activations