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

    Neuronpedia

    INDEX
    Explanations

    understanding one's own

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     splendour
    0.47
     еще
    0.46
     sólo
    0.45
     Sólo
    0.44
    োয়া
    0.41
     столько
    0.40
     şi
    0.39
     artefacts
    0.39
    Whilst
    0.38
    Favourite
    0.38
    POSITIVE LOGITS
    Ess
    0.46
     ，
    0.43
    》。
    0.42
    ।।
    0.42
    。。
    0.42
     。,
    0.40
    澎
    0.40
    "，
    0.39
     Ess
    0.39
    .。
    0.39
    Act Density 0.000%

    No Known Activations