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

    Neuronpedia

    INDEX
    Explanations

    references to programming concepts and data structures

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

    Followed by programming-related terms

    np_acts-logits-general · gemini-2.0-flash

    programming terms and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.85
     itſelf
    -0.75
     Shakspeare
    -0.71
     contextLoads
    -0.67
    (&:
    -0.66
    PageIndex
    -0.62
     themſelves
    -0.62
    setArguments
    -0.61
     houſe
    -0.60
     Majefty
    -0.59
    POSITIVE LOGITS
     tmp
    0.86
     temp
    0.86
     result
    0.77
    tmp
    0.74
     old
    0.74
    temp
    0.73
     res
    0.68
     aux
    0.65
     tem
    0.63
     new
    0.60
    Act Density 0.101%

    No Known Activations