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

    Neuronpedia

    INDEX
    Explanations

    punctuation and characters related to programming syntax

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

    user input, system output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isContained
    -0.54
    elemField
    -0.50
    setVerticalGroup
    -0.46
    
    -0.45
     royaume
    -0.41
    sitive
    -0.41
    Notae
    -0.40
    StoryboardSegue
    -0.40
     istrinya
    -0.40
    moveToFirst
    -0.39
    POSITIVE LOGITS
    udnio
    0.41
     FetchType
    0.40
    :✨
    0.40
     veget
    0.39
    NegativeButton
    0.38
     chao
    0.38
     мәкал
    0.37
    累了
    0.37
    aarrggbb
    0.37
     nahilalakip
    0.37
    Act Density 0.002%

    No Known Activations