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

    Neuronpedia

    INDEX
    Explanations

    Random text and numbers

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens—digits, numbers, and decimal values—especially standalone counts or measurements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Mess
    -0.07
     Configure
    -0.06
     dc
    -0.06
     ف
    -0.06
     à
    -0.06
     prompt
    -0.06
     Spart
    -0.06
     Kidd
    -0.06
     yếu
    -0.06
     Repeat
    -0.06
    POSITIVE LOGITS
    LIB
    0.07
    cycle
    0.06
     loads
    0.06
    ませ
    0.06
     mínimo
    0.06
    iotics
    0.06
    .assertNot
    0.06
    .MON
    0.06
     程
    0.06
    马
    0.06
    Act Density 0.134%

    No Known Activations