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

    Neuronpedia

    INDEX
    Explanations

    numerical patterns or sequences

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

    Follows parentheses or angle brackets

    np_acts-logits-general · gemini-2.0-flash

    legal citations and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    -0.93
    MOUTH
    -0.89
    CommandText
    -0.79
    KommentareTeilen
    -0.75
    Портал
    -0.75
    mouth
    -0.72
    gdx
    -0.71
    crollView
    -0.71
    WriteLiteral
    -0.70
     Popp
    -0.69
    POSITIVE LOGITS
     للمعارف
    0.81
     sogget
    0.72
    )"),
    0.69
    :].
    0.69
    wój
    0.68
     trouvera
    0.67
     Winfield
    0.66
    ]),
    0.65
    quele
    0.64
     crois
    0.64
    Act Density 0.392%

    No Known Activations