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

    Neuronpedia

    INDEX
    Explanations

    concentrations

    np_max-act · gemini-2.0-flash

    The neuron mainly activates on numeric measurements and decimal values in scientific text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    γγελ
    -0.08
    CppGenericClass
    -0.06
     visiting
    -0.06
     '{{
    -0.06
    раниц
    -0.06
    �除
    -0.06
    _tables
    -0.06
    胆
    -0.06
     molecules
    -0.06
     Increase
    -0.06
    POSITIVE LOGITS
    .AL
    0.08
     Partner
    0.07
     συν
    0.07
     gemeins
    0.07
    -L
    0.06
    offs
    0.06
    (gen
    0.06
    іг
    0.06
    Stay
    0.06
    AAD
    0.06
    Act Density 0.197%

    No Known Activations