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

    Neuronpedia

    INDEX
    Explanations

    pc

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric measurement tokens paired with units (e.g. lengths in pc or arcminutes and other quantity values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ชาว
    -0.08
     EDT
    -0.07
    AsString
    -0.06
     although
    -0.06
    Distribution
    -0.06
    　　　　　
    -0.06
    outube
    -0.06
     частини
    -0.06
     Cam
    -0.06
     اليوم
    -0.06
    POSITIVE LOGITS
    exe
    0.07
     ví
    0.07
     juris
    0.06
    �
    0.06
     risks
    0.06
     hurry
    0.06
    抓
    0.06
     apologise
    0.06
    -age
    0.06
     perror
    0.06
    Act Density 0.003%

    No Known Activations