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

    Neuronpedia

    INDEX
    Explanations

    cafe

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of cafés (cafe/café) and related coffee-shop terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sağlayan
    -0.07
     bindings
    -0.07
     rooted
    -0.07
    鸟
    -0.06
     výkon
    -0.06
    Loop
    -0.06
     Hook
    -0.06
     Rhino
    -0.06
     groin
    -0.06
     Strong
    -0.06
    POSITIVE LOGITS
     Café
    0.14
     Cafe
    0.13
     cafe
    0.12
     café
    0.12
     cafes
    0.09
     Caf
    0.09
    ..........
    0.07
     Kaf
    0.07
    afe
    0.07
     refrigerator
    0.07
    Act Density 0.006%

    No Known Activations