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

    Neuronpedia

    INDEX
    Explanations

    code snippets with numbers

    oai_token-act-pair · gemini-2.0-flash

    first-person singular pronouns

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    expandindo
    -0.84
    abestanden
    -0.80
    MLLoader
    -0.79
     Paglinawan
    -0.78
     الرياضيه
    -0.75
     للاسماء
    -0.75
     חיצוניים
    -0.75
     Савезне
    -0.73
     <=",
    -0.73
     متعلقه
    -0.73
    POSITIVE LOGITS
     i
    0.82
     u
    0.74
    i
    0.73
    u
    0.68
    f
    0.59
     f
    0.56
    is
    0.54
    us
    0.47
     as
    0.47
    ...
    0.46
    Act Density 1.722%

    No Known Activations