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

    Neuronpedia

    INDEX
    Explanations

    mentions of numerical values or counts

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

    Tokens followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    counting numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    -0.62
    1
    -0.61
    0
    -0.59
    5
    -0.57
    bahnhof
    -0.57
    3
    -0.56
     насељу
    -0.53
    9
    -0.53
    4
    -0.53
     Bakan
    -0.53
    POSITIVE LOGITS
     rhestr
    0.78
    webElementXpaths
    0.72
     Fournier
    0.72
     <>",
    0.72
    aarrggbb
    0.72
     كومونز
    0.72
    ——-
    0.70
    ;++
    0.69
    fold
    0.68
     Geraadpleegd
    0.68
    Act Density 0.404%

    No Known Activations