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

    Neuronpedia

    INDEX
    Explanations

    iterators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    משחק
    -0.07
    התייחס
    -0.06
    Ӆ
    -0.06
    ローン
    -0.06
    %，
    -0.06
    illard
    -0.06
     professionals
    -0.06
    丨
    -0.06
    _travel
    -0.06
     يحتاج
    -0.06
    POSITIVE LOGITS
    _H
    0.07
    ddit
    0.07
     thinly
    0.07
    _ylim
    0.07
    쳤
    0.07
     palace
    0.07
     Kath
    0.07
    %M
    0.07
    езульт
    0.07
    IndexOf
    0.06
    Act Density 0.012%

    No Known Activations