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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on floating‐point numeric tokens (i.e. decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ющ
    -0.06
    -money
    -0.06
     dime
    -0.06
     ancor
    -0.06
    ُو
    -0.06
    neau
    -0.06
    Rad
    -0.06
     outr
    -0.06
     wohl
    -0.06
    งของ
    -0.06
    POSITIVE LOGITS
     hend
    0.07
     gradient
    0.07
     unto
    0.06
     матері
    0.06
     MP
    0.06
    banks
    0.06
     ctr
    0.06
    low
    0.06
    _ctx
    0.06
    trl
    0.06
    Act Density 0.001%

    No Known Activations