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

    Neuronpedia

    INDEX
    Explanations

    convicted

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of a defendant’s conviction in judicial opinions, i.e. occurrences of the word “convicted.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.07
    енную
    -0.06
     виник
    -0.06
     newcomer
    -0.06
     underwent
    -0.06
    를
    -0.06
    Gary
    -0.06
    StringLength
    -0.06
    RecyclerView
    -0.06
     cancellation
    -0.06
    POSITIVE LOGITS
    scr
    0.06
     vant
    0.06
     [/
    0.06
    ालक
    0.06
    Source
    0.06
    igner
    0.06
     vip
    0.06
     AABB
    0.06
    erah
    0.06
     رضا
    0.06
    Act Density 0.005%

    No Known Activations