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

    Neuronpedia

    INDEX
    Explanations

    coding and programming syntax elements

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

    caring for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hånd
    -0.35
     ComVisible
    -0.35
    crite
    -0.33
     laiton
    -0.31
    ngdoc
    -0.31
    既
    -0.31
    ホ
    -0.30
    -0.30
    ho
    -0.29
    #
    -0.29
    POSITIVE LOGITS
     propOrder
    0.86
     ſelbſt
    0.71
     ſehr
    0.71
    BibitemShut
    0.69
     geſch
    0.68
     nakalista
    0.68
     dieſer
    0.67
     ſein
    0.67
     تضيفلها
    0.66
     dieſem
    0.65
    Act Density 0.003%

    No Known Activations