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

    Neuronpedia

    INDEX
    Explanations

    Rankings on lists

    np_max-act · gemini-2.0-flash

    This neuron detects references to numerical data—especially rankings, chart positions, years, or other figures in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     willingness
    -0.07
     hunter
    -0.07
    )arg
    -0.06
     orientation
    -0.06
     Denis
    -0.06
     Lighting
    -0.06
     místní
    -0.06
     politician
    -0.06
    เซ
    -0.06
     Declarations
    -0.06
    POSITIVE LOGITS
    IF
    0.07
     Bitmap
    0.07
     neh
    0.07
    riad
    0.06
    iê
    0.06
     latency
    0.06
    lıklı
    0.06
    Viet
    0.06
    ωμα
    0.06
     품
    0.06
    Act Density 0.009%

    No Known Activations