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

    Neuronpedia

    INDEX
    Explanations

    relative

    np_max-act · gemini-2.0-flash

    The neuron detects floating-point numeric values (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Gunn
    -0.08
     Wagner
    -0.08
     Ingram
    -0.07
     utterly
    -0.07
    -May
    -0.07
     ngờ
    -0.07
     Bain
    -0.07
     Jun
    -0.07
     Song
    -0.06
     Moon
    -0.06
    POSITIVE LOGITS
     relative
    0.12
     Relative
    0.09
    LES
    0.09
    lere
    0.08
     relatives
    0.08
     Relatives
    0.08
    le
    0.08
    ле
    0.08
     reduce
    0.08
    LEV
    0.08
    Act Density 0.009%

    No Known Activations