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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron detects floating-point numeric literals (decimal numbers) in SVG/XML path data.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Фор
    -0.07
    _Pin
    -0.07
     Resolution
    -0.07
    Su
    -0.07
     gó
    -0.06
    ภาพ
    -0.06
     Turnbull
    -0.06
     Vit
    -0.06
    нав
    -0.06
    ерш
    -0.06
    POSITIVE LOGITS
    ้ผ
    0.07
     때문에
    0.06
    ользов
    0.06
    �게
    0.06
    OFFSET
    0.06
    _STD
    0.06
     Tong
    0.06
     thời
    0.06
     auth
    0.06
     مورد
    0.06
    Act Density 0.004%

    No Known Activations