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

    Neuronpedia

    INDEX
    Explanations

    decryption and cute mate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Phal
    0.91
    Kas
    0.89
     Allentown
    0.85
     QH
    0.85
     Janis
    0.83
     Spiral
    0.83
     CCOC
    0.83
     Waltham
    0.82
     Antib
    0.82
     Watkins
    0.82
    POSITIVE LOGITS
     Maje
    1.00
     Prado
    0.96
     Arya
    0.94
    Ary
    0.88
     আলে
    0.87
     Aria
    0.86
     Bade
    0.85
     Freeman
    0.84
    عدة
    0.83
    Duke
    0.82
    Act Density 1.425%

    No Known Activations