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

    Neuronpedia

    INDEX
    Explanations

    sections of text that include formal terms or definitions

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

    preceding capitalized words

    np_acts-logits-general · gemini-2.0-flash

    introductions and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.86
     Paglinawan
    -0.84
     kasarigan
    -0.84
    ^(@)
    -0.82
    ſelves
    -0.76
    Хьажоргаш
    -0.76
     -->>
    -0.76
    Viitteet
    -0.74
    Portály
    -0.74
     esternos
    -0.74
    POSITIVE LOGITS
      
    1.21
       
    1.06
                                   
    1.05
          
    1.05
                
    0.96
    <u>
    0.96
              
    0.96
               
    0.94
                      
    0.94
                     
    0.93
    Act Density 0.450%

    No Known Activations