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

    Neuronpedia

    INDEX
    Explanations

    words that are related to the process of explaining something

    oai_token-act-pair · gemini-2.0-flash

    knowledge and information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.72
    FormTagHelper
    -0.58
    HomeAsUpEnabled
    -0.54
     disponibilités
    -0.54
     pint
    -0.52
     légales
    -0.52
     Pint
    -0.52
     kata
    -0.50
     kema
    -0.49
     Docket
    -0.49
    POSITIVE LOGITS
     varmt
    0.60
    MENAFN
    0.60
    NOPQRST
    0.59
    calipsis
    0.57
     חיצוניים
    0.57
    saraba
    0.56
    encodeWith
    0.55
    ValueStyle
    0.54
    riwal
    0.54
     الاطلاع
    0.53
    Act Density 1.348%

    No Known Activations