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

    Neuronpedia

    INDEX
    Explanations

    quantities of time

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects numeric tokens and number words—markers of counts, list items, or numbered sequences.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
     getAll
    0.31
     with
    0.27
     Various
    0.27
     与
    0.26
     getKey
    0.26
     Immunology
    0.26
     Resource
    0.26
     WITH
    0.25
     Amount
    0.25
    キー
    0.25
    POSITIVE LOGITS
     months
    0.43
    months
    0.42
     weeks
    0.41
    weeks
    0.39
     dozen
    0.37
     days
    0.36
    years
    0.36
     years
    0.35
     maanden
    0.35
     puluh
    0.34
    Act Density 0.108%

    No Known Activations