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

    Neuronpedia

    INDEX
    Explanations

    Quotations

    np_max-act · gemini-2.0-flash

    The neuron consistently fires on the very first words (and ellipses) immediately following an opening quotation mark, i.e. the start of a quoted passage.

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

    discussions related to cultural identity and heritage.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    τηγορία
    -0.07
    }while
    -0.07
    /j
    -0.06
    ailable
    -0.06
    popular
    -0.06
    _Query
    -0.06
    (valor
    -0.06
     sanity
    -0.06
    usta
    -0.06
    ξε
    -0.06
    POSITIVE LOGITS
    dll
    0.06
     شو
    0.06
     Falling
    0.06
    KT
    0.06
     그러나
    0.06
     parç
    0.06
    管
    0.06
     зуст
    0.06
     PHYS
    0.06
     गर
    0.06
    Act Density 0.018%

    No Known Activations