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

    Neuronpedia

    INDEX
    Explanations

    ED

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on the “ED” fragment in the uppercase heading “UNITED STATES,” effectively detecting the “UNITED STATES” label in document headings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ,index
    -0.07
    Decor
    -0.07
    _Box
    -0.06
    Dam
    -0.06
     знов
    -0.06
    aaaaaaaa
    -0.06
    —for
    -0.06
    ioms
    -0.06
    orsk
    -0.06
     sideways
    -0.06
    POSITIVE LOGITS
     United
    0.17
     UNITED
    0.13
    United
    0.12
     united
    0.08
     unite
    0.08
    .Positive
    0.07
     liên
    0.07
     married
    0.07
    FT
    0.07
    UNIT
    0.07
    Act Density 0.009%

    No Known Activations