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

    Neuronpedia

    INDEX
    Explanations

    git clone and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    এছাড়া
    0.92
    См
    0.91
    летнего
    0.88
     MaterialApp
    0.86
    ującego
    0.86
    ריה
    0.84
    Alternatively
    0.84
     nullptr
    0.84
    Displays
    0.83
    鬱
    0.83
    POSITIVE LOGITS
    ↵↵
    0.80
      
    0.72
     esfuerzos
    0.71
     Nancy
    0.69
     US
    0.67
     F
    0.67
        
    0.66
    ↵
    0.65
     Michelle
    0.65
     amerik
    0.63
    Act Density 1.072%

    No Known Activations