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

    Neuronpedia

    INDEX
    Explanations

    coordinates and lines

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens (especially decimal numbers), i.e. it detects numbers in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ้องพ
    -0.07
     kuş
    -0.07
     jenom
    -0.06
     vešker
    -0.06
     สพป
    -0.06
     deleted
    -0.06
    _APB
    -0.06
    írk
    -0.06
     galleries
    -0.06
    Americ
    -0.06
    POSITIVE LOGITS
     cairo
    0.07
    min
    0.07
    max
    0.07
    caf
    0.07
    macro
    0.07
     jl
    0.07
     apro
    0.06
    (ListNode
    0.06
     ilaç
    0.06
    ０
    0.06
    Act Density 0.009%

    No Known Activations