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

    Neuronpedia

    INDEX
    Explanations

    structured data formats and paths in a system

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

    lua font loader scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -1.30
     ब्रेकडाउन
    -1.19
    AndEndTag
    -1.09
     queſta
    -1.05
    parsedMessage
    -1.04
    ftagPool
    -1.03
    IsMutable
    -1.02
     للاسماء
    -1.02
    <unused41>
    -1.00
    ロウィン
    -1.00
    POSITIVE LOGITS
    </strong>
    0.41
    ing
    0.38
    os
    0.38
    </b>
    0.37
    }
    0.36
     
    0.34
    ng
    0.34
    2
    0.34
    ↵↵
    0.34
    //
    0.34
    Act Density 0.112%

    No Known Activations