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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of a company’s duration of experience—that is, numeric references to years or decades of operation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .NORMAL
    -0.06
    VIP
    -0.06
    Nov
    -0.06
     铁
    -0.06
    _tuples
    -0.06
     humble
    -0.06
     exterior
    -0.06
    nx
    -0.06
     Process
    -0.06
    _coll
    -0.06
    POSITIVE LOGITS
    juries
    0.07
    决
    0.07
     metaData
    0.07
     elles
    0.06
    /action
    0.06
    }<
    0.06
    ارية
    0.06
     frags
    0.06
    soles
    0.06
    ented
    0.06
    Act Density 0.017%

    No Known Activations