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

    Neuronpedia

    INDEX
    Explanations

    Pokémon

    np_max-act · gemini-2.0-flash

    The neuron is tuned to detect occurrences of the word “Pokémon” (or its variant “Pokemon”) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Des
    -0.06
    mobx
    -0.06
     cube
    -0.06
    روس
    -0.06
     ants
    -0.06
    ircles
    -0.06
     hans
    -0.06
    股份有限公司
    -0.06
    .Cookies
    -0.06
     reader
    -0.06
    POSITIVE LOGITS
     Pokemon
    0.11
     pokemon
    0.11
     Pokémon
    0.10
    pokemon
    0.08
    Pokemon
    0.07
    iệng
    0.07
    émon
    0.07
     pam
    0.07
    ukan
    0.07
    iken
    0.06
    Act Density 0.003%

    No Known Activations