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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting marks that appear in the text

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

    preceding capitalized words

    np_acts-logits-general · gemini-2.0-flash

    Meanwhile

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    termine
    -0.50
    Показать
    -0.49
     =
    -0.48
     […]
    -0.48
    ंटर
    -0.47
    γου
    -0.46
    fjspx
    -0.45
    ubro
    -0.45
    =[[
    -0.45
     Exam
    -0.45
    POSITIVE LOGITS
     digress
    0.85
    endphp
    0.84
     ostavi
    0.79
    enderror
    0.78
     للمعارف
    0.76
    Meanwhile
    0.73
     numberOfRows
    0.71
     دیکھیے
    0.71
     meanwhile
    0.70
    さて
    0.70
    Act Density 0.212%

    No Known Activations