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

    Neuronpedia

    INDEX
    Explanations

    low quantity or degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     boven
    0.90
    越大
    0.88
     yüksek
    0.84
     higher
    0.84
    max
    0.84
     üst
    0.84
     larger
    0.84
     hög
    0.82
    Max
    0.81
     Higher
    0.81
    POSITIVE LOGITS
    降低
    2.27
     lowering
    2.22
     lowered
    2.16
     lowers
    2.03
    低
    2.01
    Lower
    2.01
     lower
    2.01
     reduced
    1.99
     reductions
    1.99
     low
    1.97
    Act Density 1.288%

    No Known Activations