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

    Neuronpedia

    INDEX
    Explanations

    quotations

    np_max-act · gemini-2.0-flash

    This neuron activates on the boundaries and content of quoted speech, essentially spotting dialogue markers (quotation marks and the words immediately inside them).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Oscars
    -0.07
    	lp
    -0.07
    atte
    -0.06
     ele
    -0.06
    periences
    -0.06
     Mohammed
    -0.06
     illustrate
    -0.06
     rede
    -0.06
     Plants
    -0.06
    、小
    -0.06
    POSITIVE LOGITS
     olay
    0.07
    .println
    0.07
    Caller
    0.07
    .SDK
    0.06
    Ground
    0.06
     opposite
    0.06
     peacefully
    0.06
    ể
    0.06
    キャ
    0.06
    istrator
    0.06
    Act Density 0.033%

    No Known Activations