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

    Neuronpedia

    INDEX
    Explanations

    connections to personal experiences and significant relationships

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

    importance or value

    np_acts-logits-general · gemini-2.0-flash

    importance of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.87
     оригіналу
    -0.80
     مرئيه
    -0.77
    oredCriteria
    -0.76
    =$?
    -0.75
    alyptus
    -0.70
    Sucesor
    -0.69
    UnusedPrivate
    -0.68
    Diweddarwch
    -0.66
     يتيمه
    -0.66
    POSITIVE LOGITS
     importance
    1.22
     importância
    1.08
     significance
    1.06
     important
    1.04
    importance
    1.01
     importancia
    1.01
     Importance
    0.99
    important
    0.97
     اهمیت
    0.90
    Importance
    0.88
    Act Density 0.165%

    No Known Activations