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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating contrast or contradiction

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

    comparisons and emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.54
     FormBuilder
    -0.45
     ویکی‌پدی
    -0.42
    Hentet
    -0.41
    تقاوى
    -0.41
    ]})
    -0.41
     buckwheat
    -0.41
    enderror
    -0.40
    最快更新
    -0.40
    ähteet
    -0.39
    POSITIVE LOGITS
    なんと
    0.50
    brigens
    0.49
    برى
    0.44
    ListGroup
    0.44
    何と
    0.44
    ۜ
    0.43
    featureID
    0.43
     navíc
    0.43
     surprise
    0.43
     sorpresa
    0.42
    Act Density 0.160%

    No Known Activations