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

    Neuronpedia

    INDEX
    Explanations

    comment-like structures or annotations in the code

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

    code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.61
    Jeografia
    -0.55
    rungsseite
    -0.54
    лтемелер
    -0.52
     pinulongan
    -0.50
    TagMode
    -0.48
     Wikimedijinoj
    -0.47
    IndentedString
    -0.45
    ChildScrollView
    -0.44
    fromnode
    -0.44
    POSITIVE LOGITS
     Rook
    0.50
    alli
    0.49
    strator
    0.49
     Shell
    0.48
     Leaf
    0.47
     Fair
    0.47
    stock
    0.47
    abo
    0.47
    hel
    0.46
    usal
    0.46
    Act Density 0.014%

    No Known Activations