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

    Neuronpedia

    INDEX
    Explanations

    Questions

    np_max-act · gemini-2.0-flash

    The neuron is primarily responsive to personal pronouns used in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     contemporary
    -0.07
    clipse
    -0.07
     style
    -0.06
     pojištění
    -0.06
     석
    -0.06
    WISE
    -0.06
     fine
    -0.06
     المع
    -0.06
    กลาง
    -0.06
     trained
    -0.06
    POSITIVE LOGITS
    nin
    0.07
     drafting
    0.06
     ملی
    0.06
    âu
    0.06
    roducing
    0.06
    &);↵↵
    0.06
    Priority
    0.06
    uede
    0.06
     سین
    0.06
    Bezier
    0.06
    Act Density 0.051%

    No Known Activations