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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and significant identifiers in text

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

    titles and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.60
     estekak
    -0.57
    exitRule
    -0.52
    oredCriteria
    -0.52
     surla
    -0.51
    parsedMessage
    -0.49
     мәкал
    -0.47
    Personendaten
    -0.46
     שוליים
    -0.45
    UnusedPrivate
    -0.44
    POSITIVE LOGITS
    \{\\
    0.54
    ⎩
    0.45
     față
    0.43
    uxxxx
    0.43
    isbol
    0.42
    ophanes
    0.42
    illium
    0.41
    +:+
    0.41
    enservice
    0.41
    fall
    0.40
    Act Density 0.536%

    No Known Activations