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

    Neuronpedia

    INDEX
    Explanations

    sub

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yielding
    -0.25
    æijĩ头
    -0.25
    avor
    -0.24
    æģ¨
    -0.24
    jah
    -0.24
    ç«£
    -0.24
    æľīæĦı
    -0.24
     brid
    -0.24
    çĹĽ
    -0.24
    两家
    -0.23
    POSITIVE LOGITS
    èĩªå¾ĭ
    0.30
     Inside
    0.27
    åħ±åĴĮ
    0.26
    åĪĨä¼ļ
    0.26
    èIJĮ
    0.26
    egas
    0.26
    éĿ¢åIJij
    0.25
    çķİ
    0.25
    ellen
    0.25
    fony
    0.24
    Act Density 0.004%

    No Known Activations