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

    Neuronpedia

    INDEX
    Explanations

    discovery, explanation

    np_max-act · gemini-2.0-flash

    references to modern technological innovations or inventions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron responds to mentions of humans or the word “human.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     IF
    -0.07
    илися
    -0.06
     Kot
    -0.06
     ring
    -0.06
    Ｙ
    -0.06
     rejected
    -0.06
     gaming
    -0.06
     prer
    -0.06
    _PAGE
    -0.06
     applicants
    -0.06
    POSITIVE LOGITS
    λοι
    0.07
     ItemStack
    0.07
    Nova
    0.07
     hôm
    0.06
     avons
    0.06
     Αγ
    0.06
     %+
    0.06
    航空
    0.06
    _INTERVAL
    0.06
    gratis
    0.06
    Act Density 0.036%

    No Known Activations