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

    Neuronpedia

    INDEX
    Explanations

    references to capacity, especially in a quantitative context

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

    capacity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.52
    ırken
    -0.48
     Went
    -0.46
     Mön
    -0.43
    then
    -0.41
    -
    -0.41
     bolt
    -0.40
    hom
    -0.38
    Mo
    -0.38
     Зак
    -0.38
    POSITIVE LOGITS
     Capacity
    1.54
    Capacity
    1.54
    capacity
    1.49
     capacity
    1.46
     CAPACITY
    1.39
    CAPACITY
    1.31
     capacities
    1.28
     kapac
    1.13
     capacidad
    1.11
     capacité
    1.02
    Act Density 0.006%

    No Known Activations