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

    Neuronpedia

    INDEX
    Explanations

    queries related to coding and programming concepts

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

    Followed by prepositions, articles, or punctuation

    np_acts-logits-general · gemini-2.0-flash

    technical specification resolution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.41
     Lu
    -0.37
    msgTypes
    -0.34
     so
    -0.33
     pre
    -0.33
    utuhan
    -0.32
     Ju
    -0.31
     So
    -0.31
     $
    -0.30
     female
    -0.30
    POSITIVE LOGITS
    帖最后由
    0.68
    Diweddarwch
    0.66
     noDo
    0.65
     zuſammen
    0.65
     arşivlendi
    0.64
     المعيارى
    0.63
    ItemBackground
    0.63
    ⤒
    0.63
     myſelf
    0.61
     beſti
    0.61
    Act Density 1.177%

    No Known Activations