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

    Neuronpedia

    INDEX
    Explanations

    levels and costs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     solitons
    0.30
    …).
    0.30
    而不是
    0.28
     aberrations
    0.27
     grenades
    0.27
     pierres
    0.26
     čega
    0.26
     sleepers
    0.26
    ?).
    0.26
     fluids
    0.26
    POSITIVE LOGITS
    ・
    0.37
     اكتب
    0.30
     write
    0.29
            
    0.28
    0.28
        
    0.28
     $)$
    0.28
                    
    0.27
                 
    0.27
    write
    0.27
    Act Density 0.238%

    No Known Activations