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

    Neuronpedia

    INDEX
    Explanations

    coffee, barista, lattes

    np_max-act · gemini-2.0-flash

    This neuron fires on the Russian word “кофе” (coffee).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cực
    -0.08
     filme
    -0.07
    /music
    -0.07
     swollen
    -0.07
    ocular
    -0.06
     slaughter
    -0.06
     Gratuit
    -0.06
    vae
    -0.06
    els
    -0.06
    wins
    -0.06
    POSITIVE LOGITS
     Coffee
    0.07
    (sym
    0.07
    ]));
    0.07
    )])↵
    0.06
     evid
    0.06
     Sab
    0.06
     nejd
    0.06
    Jake
    0.06
    NAMESPACE
    0.06
     possessing
    0.06
    Act Density 0.054%

    No Known Activations