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

    Neuronpedia

    INDEX
    Explanations

    Brazilians

    np_max-act · gemini-2.0-flash

    The neuron responds to tokens containing Portuguese‐style diacritical marks (accented letters).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     IDX
    -0.07
     participated
    -0.06
    kaz
    -0.06
     Fluent
    -0.06
     hl
    -0.06
    folder
    -0.06
     ata
    -0.06
    onto
    -0.06
    hesion
    -0.06
    ient
    -0.06
    POSITIVE LOGITS
     принимать
    0.07
    ⌒
    0.07
     migliori
    0.07
    สนาม
    0.06
     (*)
    0.06
    ebi
    0.06
     kindly
    0.06
     �
    0.06
     Bankası
    0.06
    _ctxt
    0.06
    Act Density 0.028%

    No Known Activations