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

    Neuronpedia

    INDEX
    Explanations

    calculating remainders

    np_max-act · gemini-2.0-flash

    This neuron fires on the numeric tokens that represent the computed remainders in “What is the remainder …” style questions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     intimidating
    -0.06
    servers
    -0.06
     Hin
    -0.06
    -driver
    -0.06
     있던
    -0.06
     dag
    -0.06
    rss
    -0.06
     دارای
    -0.06
     jwt
    -0.06
     ':
    -0.06
    POSITIVE LOGITS
    HTML
    0.06
     Train
    0.06
     автомоб
    0.06
     Expense
    0.06
     Nickel
    0.06
    冬
    0.06
     Cha
    0.06
     richt
    0.06
    Voice
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵
    0.06
    Act Density 0.005%

    No Known Activations