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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate deep examination or reflection on a topic

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

    expanding or elaborating on topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Vidite
    -0.74
    出版年
    -0.59
     برانيه
    -0.56
    Personendaten
    -0.54
    </tfoot>
    -0.48
    
    -0.47
     Administrativna
    -0.47
     مرئيه
    -0.46
    Kanpo
    -0.46
     Numerade
    -0.46
    POSITIVE LOGITS
     dwelling
    0.45
     dwelt
    0.42
     dwell
    0.41
     membahas
    0.40
     revient
    0.40
    Concrete
    0.39
     concrete
    0.39
    concrete
    0.38
     soffer
    0.37
     ModelExpression
    0.37
    Act Density 0.033%

    No Known Activations