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

    Neuronpedia

    INDEX
    Explanations

    import os

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ความ
    1.08
     Sự
    1.08
    freien
    1.08
    :(
    1.05
     liye
    1.05
    dx
    1.04
    РА
    1.03
    ΕΣ
    1.03
     জন্য
    1.02
     เส
    1.02
    POSITIVE LOGITS
     pianos
    0.96
     roadblock
    0.91
     stanza
    0.89
     bastard
    0.88
     propriet
    0.88
     noodle
    0.88
     personas
    0.87
     barrier
    0.87
     parola
    0.87
     rope
    0.86
    Act Density 0.273%

    No Known Activations