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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    The neuron detects numeric measurement tokens, especially floating‐point numbers (decimal values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     日期
    -0.07
     plainly
    -0.07
    Produ
    -0.07
    иплом
    -0.06
     중요
    -0.06
    osten
    -0.06
     türü
    -0.06
    ubah
    -0.06
    IPHER
    -0.06
    罚
    -0.06
    POSITIVE LOGITS
     sparkle
    0.07
     countered
    0.06
     Cow
    0.06
     hợp
    0.06
     administrator
    0.06
     privileges
    0.06
    istant
    0.06
     извест
    0.05
    عر
    0.05
     Rain
    0.05
    Act Density 0.044%

    No Known Activations