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

    Neuronpedia

    INDEX
    Explanations

    recursion or self reference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ycznych
    0.42
    nelles
    0.40
     Subsect
    0.40
    pyplot
    0.39
    ູບ
    0.38
     zel
    0.37
     해주
    0.37
    乐趣
    0.37
     Mbappe
    0.37
     чуде
    0.36
    POSITIVE LOGITS
    бран
    0.41
    Rand
    0.40
    review
    0.40
    Render
    0.38
    vill
    0.38
     produce
    0.38
    indi
    0.38
     render
    0.38
    clar
    0.37
     review
    0.37
    Act Density 0.000%

    No Known Activations