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

    Neuronpedia

    INDEX
    Explanations

    instances of common contractions used in conversational or informal contexts

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

    negated auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.61
    Autoritní
    -0.57
     autorytatywna
    -0.54
    出版年
    -0.50
     CanadaChoose
    -0.49
     للاسماء
    -0.49
    roient
    -0.48
    Scienti
    -0.48
    ftagPool
    -0.48
    brainly
    -0.48
    POSITIVE LOGITS
     Wirklichkeit
    0.40
     चीज़ों
    0.38
     génération
    0.36
     verità
    0.36
     Realität
    0.35
    MarshalTo
    0.35
    MathML
    0.34
     sentenza
    0.33
    ThroughAttribute
    0.33
    couverte
    0.33
    Act Density 0.057%

    No Known Activations