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

    Neuronpedia

    INDEX
    Explanations

    commandments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    к
    1.23
    ни
    1.16
    ر
    1.13
    κ
    0.98
    نج
    0.97
    ১৬
    0.95
    σ
    0.95
    poon
    0.95
    સ
    0.93
    iy
    0.93
    POSITIVE LOGITS
     CIR
    0.91
     technic
    0.86
     따라서
    0.84
    也是
    0.80
     kiló
    0.80
     Comun
    0.79
     puissance
    0.78
     BIT
    0.78
    的な
    0.77
     gris
    0.74
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.