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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—especially decimal numbers and figure-related tokens in financial contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     bilm
    -0.07
    FX
    -0.06
     Table
    -0.06
     Grande
    -0.06
    evenodd
    -0.06
     카지노
    -0.06
     Cumhur
    -0.06
    265
    -0.06
     glaring
    -0.06
     bear
    -0.06
    POSITIVE LOGITS
     enc
    0.07
    LICENSE
    0.06
    هایی
    0.06
    (last
    0.06
    ，只
    0.06
    isol
    0.06
     листоп
    0.06
    。不过
    0.06
    زش
    0.06
    _sampler
    0.06
    Act Density 0.041%

    No Known Activations