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

    Neuronpedia

    INDEX
    Explanations

    in the meantime

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    により
    0.41
    ቂ
    0.38
     распоря
    0.37
    上一
    0.36
    下一
    0.35
    லாமல்
    0.35
     GDPPC
    0.35
    にい
    0.35
    volved
    0.35
     って
    0.35
    POSITIVE LOGITS
     moment
    0.67
     nicest
    0.63
     trenches
    0.60
    moment
    0.50
     thro
    0.49
     slightest
    0.47
     cutest
    0.46
     whirlwind
    0.46
     weeds
    0.44
     Moment
    0.44
    Act Density 0.011%

    No Known Activations