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

    Neuronpedia

    INDEX
    Explanations

    German affirmations and confirmations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     குறிப்பாக
    1.02
    특히
    0.98
     szczególnie
    0.94
     particularly
    0.92
     بشكل
    0.92
     particolarmente
    0.91
     inicialmente
    0.89
     באופן
    0.87
     özellikle
    0.87
     particularmente
    0.84
    POSITIVE LOGITS
     surely
    1.99
     তো
    1.87
     ведь
    1.87
     же
    1.77
     przec
    1.76
     Surely
    1.73
     jo
    1.70
     toch
    1.65
    Surely
    1.65
     doch
    1.63
    Act Density 0.002%

    No Known Activations