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

    Neuronpedia

    INDEX
    Explanations

    quantitative measurements and dimensions related to objects

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

    Numbers followed by a measurement

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by units or percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .*")]
    -0.71
    Portale
    -0.68
    +#+
    -0.65
    خصة
    -0.64
     صوتيه
    -0.60
    LookAnd
    -0.58
     متعلقه
    -0.57
     JpaRepository
    -0.56
     TestBed
    -0.55
     grise
    -0.54
    POSITIVE LOGITS
     US
    0.72
     Réponses
    0.69
    sizeCache
    0.60
     UK
    0.57
     USA
    0.57
    Espèce
    0.56
    ⓧ
    0.56
    US
    0.54
    USA
    0.52
     ausz
    0.50
    Act Density 0.435%

    No Known Activations