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

    Neuronpedia

    INDEX
    Explanations

    numerical values and relationships involving numbers

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

    Presence of digits or numerals

    np_acts-logits-general · gemini-2.0-flash

    numbers and digits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]**
    -0.65
     esternos
    -0.62
    MemoryWarning
    -0.59
     препратки
    -0.59
    EndTag
    -0.58
    ")[
    -0.58
    MLLoader
    -0.57
    ******/
    -0.57
    Obrázky
    -0.57
    헌
    -0.56
    POSITIVE LOGITS
     numbers
    1.16
     number
    1.01
     numeric
    0.91
     NUMBERS
    0.87
    numbers
    0.87
     Numbers
    0.85
     NUMBER
    0.85
    数字
    0.84
     Number
    0.82
    number
    0.82
    Act Density 0.524%

    No Known Activations