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

    Neuronpedia

    INDEX
    Explanations

    occurrences of periods in the text

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

    capability message

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    styleType
    -0.59
    Хьажоргаш
    -0.56
    ьажоргаш
    -0.54
    consulté
    -0.54
    mistak
    -0.52
    Географиясе
    -0.51
    Cyfarwyddwr
    -0.50
    GTCX
    -0.49
    Personendaten
    -0.49
    verwijspagina
    -0.48
    POSITIVE LOGITS
    tvguidetime
    0.46
    Personensuche
    0.40
    springframework
    0.35
    WriteLiteral
    0.34
    ufig
    0.34
     שוליים
    0.32
     belonged
    0.31
    ercizio
    0.31
     Bureau
    0.31
    Jährige
    0.31
    Act Density 0.003%

    No Known Activations