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

    Neuronpedia

    INDEX
    Explanations

    legal terminology and structures related to court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code punctuation and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -1.03
     informée
    -0.92
    [@BOS@]
    -0.90
    <pad>
    -0.90
    <unused8>
    -0.90
    <unused28>
    -0.90
    <unused41>
    -0.90
    <unused52>
    -0.90
    <unused3>
    -0.90
    <unused14>
    -0.90
    POSITIVE LOGITS
    (
    0.32
                            
    0.30
                
    0.29
     visst
    0.29
    co
    0.29
     gold
    0.29
    -
    0.28
    <
    0.28
               
    0.27
     
    0.27
    Act Density 0.448%

    No Known Activations