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

    Neuronpedia

    INDEX
    Explanations

    words indicating feasibility or practicality in tasks or situations

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

    legal and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тел
    -0.46
     Aca
    -0.38
     the
    -0.37
    arthur
    -0.37
    Ter
    -0.37
     ever
    -0.37
    Mer
    -0.37
     a
    -0.36
    rtype
    -0.36
     Busse
    -0.35
    POSITIVE LOGITS
    Personensuche
    0.63
     EconPapers
    0.63
     للمعارف
    0.61
     ब्रेकडाउन
    0.61
     gyhoeddwyd
    0.55
     linkovi
    0.54
     Autorizaciones
    0.54
     ویکی‌پدی
    0.51
     ModelExpression
    0.50
    webElementXpaths
    0.49
    Act Density 0.001%

    No Known Activations