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

    Neuronpedia

    INDEX
    Explanations

    indications of technicality or programming-related syntax and structures

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

    Text with asterisks

    np_acts-logits-general · gemini-2.0-flash

    Mechanical equipment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.68
     forfait
    -0.57
     aé
    -0.51
     cedo
    -0.50
    DebuggerStep
    -0.50
    チール
    -0.48
    fait
    -0.47
    fini
    -0.47
    garn
    -0.46
    entuh
    -0.46
    POSITIVE LOGITS
        
    0.75
          
    0.73
    +#+
    0.72
              
    0.69
     InputDecoration
    0.69
                  
    0.66
            
    0.66
           
    0.65
                      
    0.65
               
    0.64
    Act Density 0.402%

    No Known Activations