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

    Neuronpedia

    INDEX
    Explanations

    mathematical proofs

    np_max-act · gemini-2.0-flash

    The neuron responds to discussions about multiplying two primes and concluding that their product cannot itself be prime (e.g. mentions of “two primes,” “product,” “never be prime,” and “divisors”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Hide
    -0.06
     hc
    -0.06
     Cone
    -0.06
     iliş
    -0.06
    ์↵
    -0.06
    .car
    -0.06
    (cmd
    -0.06
    811
    -0.06
     Tinder
    -0.06
    924
    -0.06
    POSITIVE LOGITS
     Tarif
    0.07
     stát
    0.07
    сторія
    0.07
     Amir
    0.07
    prior
    0.07
     Warsaw
    0.07
     prior
    0.07
    ิภาพ
    0.06
     stør
    0.06
     quen
    0.06
    Act Density 0.047%

    No Known Activations