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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence delimiters in text

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

    closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endam
    -0.47
     exempted
    -0.46
    mybatisplus
    -0.46
    thums
    -0.45
     الرياضيه
    -0.44
    pipes
    -0.44
     Pipes
    -0.44
     Taxonomic
    -0.43
    Хьажоргаш
    -0.43
    Cyfarwyddwr
    -0.43
    POSITIVE LOGITS
    öhne
    0.39
    ciple
    0.36
     помню
    0.36
    UnusedPrivate
    0.36
    /**
    0.35
     confianza
    0.35
    ftagPool
    0.35
     confiança
    0.35
    oredCriteria
    0.34
     unicórnio
    0.33
    Act Density 0.015%

    No Known Activations