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

    Neuronpedia

    INDEX
    Explanations

    little, less, least

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ts
    0.40
    ໝ
    0.37
    iaan
    0.36
     P
    0.33
     oraz
    0.33
    ަމ
    0.33
     allows
    0.32
    eteer
    0.32
    ema
    0.31
    ్ఞ
    0.31
    POSITIVE LOGITS
     $(<
    0.54
     chance
    0.50
     likelihood
    0.49
     직접
    0.48
     fuss
    0.47
     comparatively
    0.47
     directly
    0.46
    直接
    0.45
     appreciably
    0.44
     فرص
    0.44
    Act Density 0.027%

    No Known Activations