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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    マン
    -0.06
    �
    -0.06
    omez
    -0.06
     آدم
    -0.06
     Hebrew
    -0.06
    เ
    -0.06
     nowrap
    -0.06
     cryst
    -0.06
     похож
    -0.06
    _hist
    -0.06
    POSITIVE LOGITS
     LEG
    0.08
    Proceed
    0.07
    ¸
    0.07
     Latest
    0.07
     Ign
    0.07
    Senator
    0.07
    >({↵
    0.07
     finalist
    0.07
     resetting
    0.06
    profit
    0.06
    Act Density 0.307%

    No Known Activations