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

    Neuronpedia

    INDEX
    Explanations

    references to academic or research-related websites and formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    urls and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.67
     незавершена
    -0.63
     ویکی‌پدی
    -0.56
    tvguidetime
    -0.56
    $_['
    -0.54
    Rohy
    -0.52
    >--}}
    -0.52
     مرئيه
    -0.52
    RegressionTest
    -0.52
    ɵ
    -0.51
    POSITIVE LOGITS
    )
    0.45
    TokenNameLPAREN
    0.43
     skjer
    0.42
    ,
    0.42
    GraphicsUnit
    0.41
    we
    0.41
    ),
    0.41
    ReadLine
    0.40
    openConnection
    0.40
    uxxxx
    0.40
    Act Density 0.002%

    No Known Activations