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

    Neuronpedia

    INDEX
    Explanations

    its

    np_max-act · gemini-2.0-flash

    The neuron consistently fires on the possessive pronoun “its” when it appears in the context of reporting a place’s population in the census sentences.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    NETWORK
    -0.07
    >.</
    -0.07
     Charm
    -0.06
    Ah
    -0.06
     Roland
    -0.06
     PMID
    -0.06
     RTP
    -0.06
    (flow
    -0.06
    /material
    -0.06
     HERO
    -0.06
    POSITIVE LOGITS
    频
    0.07
     acesso
    0.07
    _CMD
    0.06
    tableFuture
    0.06
    عی
    0.06
     Province
    0.06
     liberty
    0.06
    _EC
    0.06
     antlr
    0.06
    dB
    0.06
    Act Density 0.003%

    No Known Activations