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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron activates on capitalized identifiers (e.g. class or type names) in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     downwards
    -0.07
    _DROP
    -0.06
     parach
    -0.06
     adv
    -0.06
     Venez
    -0.06
    Activities
    -0.06
     downward
    -0.06
    Eth
    -0.06
    оби
    -0.06
    วร
    -0.06
    POSITIVE LOGITS
    .setStyle
    0.06
     (.
    0.06
     دقیق
    0.06
    Opacity
    0.06
    --[[
    0.06
    .Interfaces
    0.06
    .SubElement
    0.06
    _SUITE
    0.06
     νεφοκάλυψης
    0.06
     orbs
    0.06
    Act Density 0.027%

    No Known Activations