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

    Neuronpedia

    INDEX
    Explanations

    negative correlation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ¼
    0.40
     (−
    0.40
     (-
    0.40
     domain
    0.39
     an
    0.36
     `%
    0.36
     domains
    0.36
     puts
    0.35
    %=
    0.34
     bxc
    0.34
    POSITIVE LOGITS
     realizzazione
    0.45
     этими
    0.42
    merksamkeit
    0.42
     महंगाई
    0.41
     récomp
    0.41
    Alien
    0.41
     فع
    0.41
     célébr
    0.41
    赁
    0.41
     voulait
    0.41
    Act Density 0.001%

    No Known Activations