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

    Neuronpedia

    INDEX
    Explanations

    origins and history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಸೆ
    0.70
     ښ
    0.69
     aktivieren
    0.68
     Routine
    0.68
    খের
    0.65
    ळ्या
    0.65
     করলাম
    0.65
    щение
    0.64
     увагу
    0.64
     Nicholson
    0.64
    POSITIVE LOGITS
     origin
    2.23
     origins
    2.20
     origem
    2.06
     origen
    2.01
     Origin
    1.99
    Origin
    1.98
     Origins
    1.97
    origin
    1.96
    Origins
    1.90
     originates
    1.82
    Act Density 0.742%

    No Known Activations