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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash

    The neuron fires on the indefinite pronoun “one” (and its close variants like “ones” or “only one”) whenever it appears in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    instances of regulatory compliance issues related to data protection.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     tapered
    -0.07
    肯定
    -0.07
     предполаг
    -0.07
     предпол
    -0.06
    nl
    -0.06
    istor
    -0.06
    来的
    -0.06
    ubble
    -0.06
     �
    -0.06
    ystery
    -0.06
    POSITIVE LOGITS
     *
↵
    0.07
     miles
    0.07
     cine
    0.06
     Населення
    0.06
     [];↵
    0.06
     війни
    0.06
    -'+
    0.06
    IM
    0.06
     �
    0.06
    itom
    0.05
    Act Density 0.009%

    No Known Activations