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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﾝ
    -0.07
    喜欢
    -0.07
    それが
    -0.07
    卵
    -0.06
     האחרונות
    -0.06
    ն
    -0.06
    tg
    -0.06
    ikon
    -0.06
    adin
    -0.06
    選
    -0.06
    POSITIVE LOGITS
    &amp
    0.08
     monopol
    0.07
    ,model
    0.07
    𝘇
    0.07
    ivel
    0.07
     заяв
    0.07
    OTAL
    0.07
     malls
    0.07
     traversal
    0.06
    Rel
    0.06
    Act Density 0.004%

    No Known Activations