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

    Neuronpedia

    INDEX
    Explanations

    patterns related to numeric values and mathematical operations

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

    Tokens after numbers, especially citations

    np_acts-logits-general · gemini-2.0-flash

    citations and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.87
    AndEndTag
    -0.70
     الرياضيه
    -0.59
    kuuta
    -0.57
     beginnetje
    -0.54
     OFDb
    -0.52
    zło
    -0.52
     "]";
    -0.52
    [@"
    -0.50
     الحره
    -0.48
    POSITIVE LOGITS
    8
    0.69
    9
    0.68
    ponses
    0.66
    حياتها
    0.63
    6
    0.61
    RenderAtEndOf
    0.59
    ########.
    0.57
    7
    0.57
    Зноскі
    0.56
    4
    0.55
    Act Density 0.875%

    No Known Activations