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

    Neuronpedia

    INDEX
    Explanations

    contracted forms like "let's"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
       
    0.46
    <h2>
    0.46
        
    0.45
              
    0.45
         
    0.44
    *
    0.42
    "
    0.41
    <h3>
    0.41
    ↵↵↵↵↵
    0.39
          
    0.38
    POSITIVE LOGITS
     cuffs
    0.48
     grooves
    0.46
     vassals
    0.46
     annuities
    0.45
     isotopes
    0.44
    윕
    0.43
     distributions
    0.42
     fluids
    0.42
     belts
    0.42
    сцю
    0.42
    Act Density 0.001%

    No Known Activations