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

    Neuronpedia

    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash

    The neuron fires on top‐level domain tokens—e.g. “com” in URLs.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ,set
    -0.07
     typealias
    -0.07
    .encrypt
    -0.07
     nutritious
    -0.06
    (char
    -0.06
    .Serve
    -0.06
    #=
    -0.06
    tele
    -0.06
     skincare
    -0.06
     bardzo
    -0.06
    POSITIVE LOGITS
    .VideoCapture
    0.07
     المج
    0.06
     rhythms
    0.06
    _dispatcher
    0.06
     должен
    0.06
    .JPanel
    0.06
    Ath
    0.06
     Christopher
    0.06
    egg
    0.06
     LOC
    0.06
    Act Density 0.000%

    No Known Activations