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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    This neuron specifically activates on floating‐point numeric values (numbers with a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Game
    -0.06
     MediaPlayer
    -0.06
     gee
    -0.06
    Sp
    -0.06
    _record
    -0.06
     plast
    -0.06
    Book
    -0.06
     convex
    -0.06
     administration
    -0.06
     activity
    -0.06
    POSITIVE LOGITS
    [])
    0.06
     irres
    0.06
     tho
    0.06
     mainAxisAlignment
    0.06
     پیشنهاد
    0.06
     bootloader
    0.06
    วงศ
    0.06
     disappoint
    0.06
     Despite
    0.06
     ابت
    0.06
    Act Density 0.062%

    No Known Activations