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

    Neuronpedia

    INDEX
    Explanations

    against

    np_max-act · gemini-2.0-flash

    The neuron fires on words referring to legal procedural actions (like filing, dismissing, claiming, entering orders, etc.) in a court context.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .demo
    -0.06
     '../../../../
    -0.06
    进行
    -0.06
    ($("#
    -0.06
     Ott
    -0.06
    日の
    -0.06
    --){↵
    -0.06
    แนะนำ
    -0.06
    ραβ
    -0.06
    395
    -0.06
    POSITIVE LOGITS
     Beatles
    0.07
     ARM
    0.07
     Gemini
    0.07
    (.)
    0.06
    _self
    0.06
     Towards
    0.06
    makta
    0.06
     mop
    0.06
     avan
    0.06
    筒
    0.06
    Act Density 0.009%

    No Known Activations