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

    Neuronpedia

    INDEX
    Explanations

    first-person

    np_max-act · gemini-2.0-flash

    This neuron responds to first-person references (especially the pronoun “I”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    mour
    -0.07
     diagnostic
    -0.06
     "";↵
    -0.06
     安
    -0.06
    tower
    -0.06
    %"↵
    -0.06
    ↵↵
    -0.06
     outrage
    -0.06
    況
    -0.06
     Une
    -0.06
    POSITIVE LOGITS
     SOLUTION
    0.07
    liž
    0.07
     tenemos
    0.06
     scrolled
    0.06
    `),↵
    0.06
    fgets
    0.06
    onesia
    0.06
    ürlich
    0.06
     Ao
    0.06
    asured
    0.06
    Act Density 0.120%

    No Known Activations