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

    Neuronpedia

    INDEX
    Explanations

    were

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens (quantities, percentages, and other numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Th
    -0.07
     Moscow
    -0.06
    His
    -0.06
    .getClass
    -0.06
     evenings
    -0.06
    mul
    -0.06
     Anyway
    -0.06
    amenti
    -0.05
    Sil
    -0.05
    ishment
    -0.05
    POSITIVE LOGITS
     longitudinal
    0.07
    '),↵↵
    0.07
    ندگی
    0.07
     đạo
    0.07
    :{
↵
    0.07
    _;↵
    0.07
     getDefault
    0.06
    _tbl
    0.06
     infused
    0.06
     ''
    0.06
    Act Density 0.042%

    No Known Activations