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

    Neuronpedia

    INDEX
    Explanations

    variable and first usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     riots
    0.33
     rugby
    0.29
     flamboyant
    0.29
     coal
    0.29
     clubs
    0.28
     underdog
    0.28
     stadium
    0.28
     fireworks
    0.27
     ballet
    0.27
     drumming
    0.27
    POSITIVE LOGITS
    ↵
    0.33
            
    0.32
                 
    0.32
             
    0.30
          
    0.30
                    
    0.30
    Nan
    0.30
         
    0.29
           
    0.29
    Imidazole
    0.28
    Act Density 0.000%

    No Known Activations