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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

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

    python programming imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.84
    UnusedPrivate
    -0.82
    featureID
    -0.82
    Personendaten
    -0.82
    MigrationBuilder
    -0.81
     ―――――
    -0.81
     queſta
    -0.81
    رشف
    -0.79
    ImageContext
    -0.78
    SourceChecksum
    -0.77
    POSITIVE LOGITS
    /
    0.47
    .
    0.44
    \
    0.33
     editors
    0.32
    -
    0.32
     /
    0.30
     Leser
    0.29
     translators
    0.29
    }/
    0.28
     writers
    0.28
    Act Density 0.003%

    No Known Activations