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

    Neuronpedia

    INDEX
    Explanations

    informal writing

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric tokens containing decimal points (floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     esteemed
    -0.07
    Border
    -0.07
    escort
    -0.07
    ดน
    -0.06
    documents
    -0.06
    Sarah
    -0.06
    administration
    -0.06
    ابه
    -0.06
    Thinking
    -0.06
    Cog
    -0.06
    POSITIVE LOGITS
     {}'.
    0.07
    ython
    0.07
    ันเป
    0.06
    _itr
    0.06
    ITIVE
    0.06
     Auto
    0.06
     Bên
    0.06
     Asc
    0.06
    singular
    0.06
     Filed
    0.06
    Act Density 0.098%

    No Known Activations