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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and metrics

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

    rates and ratios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.65
    transQ
    -0.59
    mergeFrom
    -0.54
    tvguidetime
    -0.53
     getTotal
    -0.51
     يتيمه
    -0.51
    bership
    -0.49
     betweenstory
    -0.49
    uxxxx
    -0.48
    RenderAtEndOf
    -0.48
    POSITIVE LOGITS
     per
    0.50
     rate
    0.45
     averaging
    0.45
    每
    0.42
    당
    0.41
    Enllaces
    0.41
     ratio
    0.40
     tertinggi
    0.40
    rate
    0.40
     düşünü
    0.39
    Act Density 0.071%

    No Known Activations