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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literal tokens—especially decimal and fractional constants in mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Hồ
    -0.07
     "@
    -0.07
     martyr
    -0.07
     Agility
    -0.07
     July
    -0.07
     combo
    -0.07
     Mold
    -0.07
     Audience
    -0.07
     성
    -0.07
     durumu
    -0.07
    POSITIVE LOGITS
     various
    0.07
    １
    0.06
     ostat
    0.06
     داو
    0.06
     کردن
    0.06
    과의
    0.06
    完
    0.06
     프
    0.06
     Verify
    0.06
     các
    0.06
    Act Density 0.008%

    No Known Activations