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

    Neuronpedia

    INDEX
    Explanations

    occurrences of line breaks or empty spaces in code or text

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

    foreign words and spellings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GE
    -0.47
            
    -0.44
    jspx
    -0.43
        
    -0.43
           
    -0.42
             
    -0.42
          
    -0.41
               
    -0.40
    XmlIgnore
    -0.40
         
    -0.40
    POSITIVE LOGITS
     Verſ
    0.65
     themſelves
    0.63
     miniaturka
    0.61
     Monfieur
    0.61
    ſcher
    0.59
    0.59
    期刊论文
    0.59
     Infór
    0.58
     nothwendig
    0.58
     ganchillo
    0.57
    Act Density 0.005%
    No Known Activations