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

    Neuronpedia

    INDEX
    Explanations

    programming language syntax and structure elements

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

    Code-related terms and programming keywords

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Frame
    -0.64
     وتسجيلات
    -0.64
     gọn
    -0.63
     kaynağından
    -0.62
     Frame
    -0.61
    df
    -0.61
    frames
    -0.59
    pd
    -0.57
    OGND
    -0.57
    ########.
    -0.56
    POSITIVE LOGITS
    GEBURTSDATUM
    0.48
     InputDecoration
    0.46
    offsetof
    0.46
    livejournal
    0.45
    ésor
    0.43
    Cordialement
    0.43
    totalTime
    0.42
    intios
    0.41
    EClass
    0.41
     class
    0.41
    Act Density 0.132%

    No Known Activations