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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal arguments or courtroom procedures

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

    legal rule citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -1.10
     desmotivaciones
    -1.07
     auffi
    -1.04
    ſcher
    -1.02
     laſſen
    -0.98
    iſen
    -0.97
    ロウィン
    -0.96
     Verſ
    -0.94
    iſchen
    -0.94
     ſche
    -0.94
    POSITIVE LOGITS
      
    0.90
       
    0.66
    0.61
          
    0.57
        
    0.57
    _
    0.55
              
    0.51
     
    0.50
                      
    0.49
    　
    0.48
    Act Density 0.014%

    No Known Activations