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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "through"

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

    indicating a range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.41
    AddTagHelper
    -0.39
     légale
    -0.34
    Ị
    -0.33
    Árbitro
    -0.33
    prepareStatement
    -0.32
    ंदीखरीदारी
    -0.31
    celana
    -0.31
    laceae
    -0.31
     CreateTagHelper
    -0.31
    POSITIVE LOGITS
     through
    1.29
    through
    1.23
     Through
    1.20
    Through
    1.20
     THROUGH
    1.10
    THROUGH
    1.07
     thru
    1.04
     attraverso
    1.01
     través
    0.94
    Thru
    0.88
    Act Density 0.008%

    No Known Activations