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

    Neuronpedia

    INDEX
    Explanations

    contempt

    np_max-act · gemini-2.0-flash

    The neuron activates on references to legal contempt charges or contempt-of-court proceedings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Alloc
    -0.07
    (each
    -0.06
    (blog
    -0.06
     вероят
    -0.06
     ιστο
    -0.06
    され
    -0.06
    .getElementsByName
    -0.06
    Vert
    -0.06
    	MD
    -0.06
     réal
    -0.06
    POSITIVE LOGITS
     contempt
    0.12
     scorn
    0.09
     disdain
    0.07
    ん
    0.07
    tone
    0.07
     desp
    0.06
    inspect
    0.06
     pet
    0.06
    green
    0.06
    CNN
    0.06
    Act Density 0.003%

    No Known Activations