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

    Neuronpedia

    INDEX
    Explanations

    formal references to articles and reports

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

    Text from news, articles, or blogs

    np_acts-logits-general · gemini-2.0-flash

    Reprinted edited published

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.52
     -
    -0.51
     even
    -0.51
    ,
    -0.47
     addirittura
    -0.47
     just
    -0.47
     zelfs
    -0.46
     it
    -0.45
    tamanya
    -0.43
     biggest
    -0.43
    POSITIVE LOGITS
     Majefty
    0.85
     pleaſure
    0.84
    hyrchwyd
    0.83
     edited
    0.79
    GEBURTSDATUM
    0.79
     Wikimedijinoj
    0.78
     ſmall
    0.78
     OMITTED
    0.77
    رشف
    0.77
     Reprinted
    0.77
    Act Density 0.275%

    No Known Activations