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

    Neuronpedia

    INDEX
    Explanations

    error handling and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     konflikt
    0.45
    plicial
    0.42
    ivided
    0.41
    >\<^
    0.41
    conflict
    0.41
    üdis
    0.40
    ifai
    0.40
     conflict
    0.40
    ោគ
    0.40
    汢
    0.40
    POSITIVE LOGITS
         
    0.48
            
    0.45
          
    0.43
     High
    0.43
     Tattoo
    0.42
      
    0.42
       
    0.42
     Near
    0.42
     Mark
    0.41
     Cli
    0.41
    Act Density 0.000%

    No Known Activations