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

    Neuronpedia

    INDEX
    Explanations

    references to programming or coding constructs

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

    finite domain extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.48
     Signalez
    -0.42
    HomeAsUpEnabled
    -0.40
    ::_('
    -0.39
    脚注の使い方
    -0.39
    UnusedPrivate
    -0.39
    ensatz
    -0.39
     оригіналу
    -0.38
     للاسماء
    -0.38
     Reverso
    -0.37
    POSITIVE LOGITS
    "]]
    0.45
    multer
    0.44
    gól
    0.42
     substituting
    0.42
    })`
    0.41
     boty
    0.41
    testcase
    0.41
    rsiniz
    0.41
     healed
    0.40
     Scouting
    0.40
    Act Density 0.157%

    No Known Activations