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

    Neuronpedia

    INDEX
    Explanations

    Conversational text

    np_max-act · gemini-2.0-flash

    The neuron is a detector for first‐person singular references (i.e. “I,” “my,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     you
    -0.09
     ess
    -0.07
     YOU
    -0.07
     your
    -0.07
     invokes
    -0.06
     yours
    -0.06
    you
    -0.06
     explosives
    -0.06
    arged
    -0.06
     você
    -0.06
    POSITIVE LOGITS
    @RunWith
    0.06
     elderly
    0.06
     알아
    0.06
    幸福
    0.06
    realloc
    0.06
     istiyor
    0.06
     relentlessly
    0.06
    erving
    0.06
     lumin
    0.06
     whore
    0.06
    Act Density 0.301%

    No Known Activations