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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of juries and jury decision-making in legal contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Jew
    -0.08
     Ashton
    -0.07
     Alone
    -0.06
     ration
    -0.06
     Highlands
    -0.06
    atomy
    -0.06
    ках
    -0.06
    _checks
    -0.06
     Kitty
    -0.06
     detention
    -0.06
    POSITIVE LOGITS
     selfie
    0.06
    _coin
    0.06
    ента
    0.06
    StandardItem
    0.06
    aleza
    0.06
     CONTEXT
    0.06
    िषय
    0.06
    giatan
    0.06
     masculinity
    0.06
    TERNAL
    0.06
    Act Density 0.010%

    No Known Activations