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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal and healthcare-related responsibilities and frameworks

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

    "and" followed by a pronoun

    np_acts-logits-general · gemini-2.0-flash

    lists joined by "and"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.76
    writeFieldEnd
    -0.62
     '\\;'
    -0.61
     للاسماء
    -0.61
    thâu
    -0.59
    Unmarshaller
    -0.57
    intios
    -0.57
    Życiorys
    -0.56
    Saison
    -0.56
     مرئيه
    -0.54
    POSITIVE LOGITS
     ourselves
    0.80
     myself
    0.76
     families
    0.72
     yourself
    0.70
     their
    0.70
     themselves
    0.69
     herself
    0.69
     animals
    0.67
     strangers
    0.64
     unborn
    0.64
    Act Density 0.295%

    No Known Activations