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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash

    class and method declarations within programming code.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on floating‐point numeric literals (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    recated
    -0.06
    號
    -0.06
    駐
    -0.06
    itzerland
    -0.06
     createContext
    -0.06
     "---
    -0.06
     článek
    -0.06
    Ë
    -0.06
    (convert
    -0.06
    interopRequireDefault
    -0.06
    POSITIVE LOGITS
     orth
    0.07
     overhaul
    0.07
    342
    0.07
    andering
    0.06
    812
    0.06
     neust
    0.06
     indian
    0.06
    rena
    0.06
     inspector
    0.06
    lastic
    0.06
    Act Density 0.016%

    No Known Activations