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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .unlink
    -0.07
    뮹
    -0.07
     conserve
    -0.06
     inserting
    -0.06
    奶
    -0.06
    INavigation
    -0.06
     deriving
    -0.06
    雲
    -0.06
    찢
    -0.06
     announc
    -0.06
    POSITIVE LOGITS
     unequal
    0.07
    ────
    0.07
    样本
    0.07
    슌
    0.07
     discour
    0.06
    _ELEM
    0.06
     fixing
    0.06
     grassroots
    0.06
    屋顶
    0.06
    ......↵↵
    0.06
    Act Density 0.004%

    No Known Activations