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

    Neuronpedia

    INDEX
    Explanations

    explicit discussion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ()-
    0.41
    Radar
    0.41
    у
    0.41
    ിച്ച്
    0.41
     Xanth
    0.41
    இவர்
    0.41
     Verbre
    0.41
    变速
    0.40
    𒌉
    0.40
     優
    0.40
    POSITIVE LOGITS
     så
    0.46
     revamp
    0.44
     ai
    0.42
     instant
    0.42
     revamped
    0.41
     sehingga
    0.41
     refreshed
    0.41
     intervention
    0.40
     lifespan
    0.40
     lebens
    0.40
    Act Density 0.000%

    No Known Activations