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

    Neuronpedia

    INDEX
    Explanations

    quantitative comparisons and changes in performance or measurements

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

    Percentage or quantity changes

    np_acts-logits-general · gemini-2.0-flash

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.51
     >=",
    -0.49
     élevée
    -0.44
     far
    -0.43
     հղումներ
    -0.43
    jsxFileName
    -0.43
     élevées
    -0.42
     paro
    -0.42
    Ссылки
    -0.42
    ItemBackground
    -0.42
    POSITIVE LOGITS
    تقاوى
    0.76
    GraphicsUnit
    0.66
    Reprints
    0.59
     pollin
    0.58
    ressi
    0.57
     betweenstory
    0.56
    istoitu
    0.56
    Demografie
    0.55
    piram
    0.55
     Δη
    0.55
    Act Density 0.397%

    No Known Activations