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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating expansion or addition

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

    The token "and"

    np_acts-logits-general · gemini-2.0-flash

    listing items or quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fjspx
    -0.70
    writeFieldEnd
    -0.67
     BnF
    -0.67
     poveznice
    -0.67
    sizeCache
    -0.63
     ویکی‌پدیا
    -0.61
    JpaRepository
    -0.61
     nakalista
    -0.60
    SharedCtor
    -0.60
    書館
    -0.59
    POSITIVE LOGITS
     plenty
    1.59
     lots
    1.52
     no
    1.19
     LOTS
    1.15
     a
    1.15
     ample
    1.11
     Lots
    1.11
    plenty
    1.11
    Lots
    1.08
    lots
    1.08
    Act Density 0.377%

    No Known Activations