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

    Neuronpedia

    INDEX
    Explanations

    CSS z-index positioning

    np_max-act · gemini-2.0-flash

    This neuron fires on common Italian function words (e.g. “che,” “sopra,” “uno,” “l’altro”) and thus identifies Italian‐language text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     внимание
    -0.07
     عزیز
    -0.06
    ropical
    -0.06
    ٌ
    -0.06
    output
    -0.06
     salt
    -0.06
    -function
    -0.06
    แชม
    -0.06
    Mongo
    -0.06
    _UNIQUE
    -0.06
    POSITIVE LOGITS
    ipheral
    0.07
     originates
    0.06
     华
    0.06
    (keys
    0.06
    -law
    0.06
    Pres
    0.06
    철
    0.06
     Peg
    0.06
    $response
    0.06
    иф
    0.06
    Act Density 0.005%

    No Known Activations