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

    Neuronpedia

    INDEX
    Explanations

    shader code and visual effects

    np_max-act · gemini-2.0-flash

    The neuron fires on floating-point numeric values (i.e. decimal numbers) in specification or code listings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     слух
    -0.07
     พฤษภาคม
    -0.07
    べて
    -0.07
     Таким
    -0.06
    _print
    -0.06
     burden
    -0.06
     ())↵
    -0.06
    епти
    -0.06
    _plugins
    -0.06
     至
    -0.06
    POSITIVE LOGITS
     Bau
    0.07
    #for
    0.07
     امر
    0.07
     overrun
    0.07
     enabled
    0.06
     neo
    0.06
    全面
    0.06
     hier
    0.06
     δεν
    0.06
     富
    0.06
    Act Density 0.013%

    No Known Activations