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

    Neuronpedia

    INDEX
    Explanations

    references to requirements or criteria

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

    end of list/quantifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.54
    odenal
    -0.43
     कीज
    -0.40
    ANDER
    -0.39
    TagMode
    -0.38
    oglio
    -0.37
    eaux
    -0.37
    engers
    -0.37
    ACO
    -0.37
    inWeight
    -0.37
    POSITIVE LOGITS
     MainAxisSize
    0.54
    </tfoot>
    0.46
    endregion
    0.45
     mergeFrom
    0.45
     怎样
    0.45
    '][]
    0.43
     arşivlendi
    0.43
     snippetHide
    0.42
    Попис
    0.42
    ExtendWith
    0.42
    Act Density 1.917%

    No Known Activations