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

    Neuronpedia

    INDEX
    Explanations

    end of query punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     programmers
    0.46
     bloggers
    0.44
    плю
    0.42
     introductory
    0.41
     blogger
    0.41
    acées
    0.40
     bayan
    0.40
     extension
    0.39
     Girlfriend
    0.39
    岑
    0.39
    POSITIVE LOGITS
            
    0.50
                
    0.46
    ↵
    0.44
    ')}
    0.44
     strcmp
    0.43
          
    0.43
              
    0.43
    ↵↵
    0.42
     Infatti
    0.42
    ')
    0.41
    Act Density 0.000%

    No Known Activations