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

    Neuronpedia

    INDEX
    Explanations

    elements of technical issues and operational configurations

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

    issues and problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ransition
    -0.45
     purpoſe
    -0.36
    częściej
    -0.34
    SuccessListener
    -0.33
     pleaſure
    -0.32
    ECONDS
    -0.32
    tawesome
    -0.31
    tdessen
    -0.31
     Jefus
    -0.31
    例句
    -0.30
    POSITIVE LOGITS
    SourceChecksum
    0.64
     Problems
    0.61
     troublesome
    0.60
    proble
    0.60
     problematic
    0.59
    trouble
    0.59
    Problems
    0.59
    Proble
    0.58
     ویکی‌پدی
    0.57
     ostavi
    0.57
    Act Density 0.106%

    No Known Activations