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

    Neuronpedia

    INDEX
    Explanations

    en

    np_max-act · gemini-2.0-flash

    The neuron activates on the French preposition “en” (i.e. occurrences of the token “en”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -0.08
    666
    -0.08
     circle
    -0.07
    rough
    -0.07
     tariff
    -0.07
    cycle
    -0.07
     brightest
    -0.07
     Marc
    -0.07
     çoğu
    -0.07
    POSIT
    -0.07
    POSITIVE LOGITS
    EN
    0.09
     En
    0.09
     EL
    0.09
    en
    0.09
    (en
    0.08
     EN
    0.08
     Ensemble
    0.08
    ENT
    0.08
    En
    0.08
    _end
    0.08
    Act Density 0.063%

    No Known Activations