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

    Neuronpedia

    INDEX
    Explanations

    numerical data and comparisons within a context

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

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Approximately
    -1.05
    Approximately
    -1.04
     approximately
    -1.03
    approximately
    -0.98
     aproximadamente
    -0.97
    nearly
    -0.88
     yaklaşık
    -0.84
     लगभग
    -0.84
    Nearly
    -0.84
     nearly
    -0.82
    POSITIVE LOGITS
     ten
    0.91
     hundred
    0.71
     fifty
    0.69
     tenth
    0.69
     half
    0.67
     десять
    0.66
    RuleContext
    0.66
     dieci
    0.63
     zehn
    0.63
     Ten
    0.62
    Act Density 0.457%

    No Known Activations