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

    Neuronpedia

    INDEX
    Explanations

    keywords or phrases indicating a summary or conclusion

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

    followed by capitalized words

    np_acts-logits-general · gemini-2.0-flash

    beginning of quotation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.86
     AttributeSet
    -0.81
    queryInterface
    -0.81
    SBATCH
    -0.80
    FTFY
    -0.80
    Архівовано
    -0.77
     defaultstate
    -0.77
     تضيفلها
    -0.75
    AllAfrica
    -0.74
     الرياضيه
    -0.74
    POSITIVE LOGITS
    We
    1.06
    The
    1.00
    I
    0.94
    There
    0.94
    It
    0.90
    When
    0.88
    This
    0.84
    A
    0.84
    If
    0.77
    As
    0.76
    Act Density 0.145%

    No Known Activations