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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron responds to passages rich in numeric data (dates, measurements, statistics), essentially flagging text that contains numbers or other quantitative details.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     balancing
    -0.07
     Counts
    -0.07
    expired
    -0.07
     undefeated
    -0.06
    ารถ
    -0.06
     SPF
    -0.06
    vertise
    -0.06
    PV
    -0.06
     demol
    -0.06
     보
    -0.06
    POSITIVE LOGITS
     léč
    0.07
    -inc
    0.06
    ="./
    0.06
     buyers
    0.06
     rosa
    0.06
    ників
    0.06
     ''),
    0.06
    .VisualStudio
    0.06
    ğı
    0.06
    etAddress
    0.06
    Act Density 0.108%

    No Known Activations