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

    Neuronpedia

    INDEX
    Explanations

    for students

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    迪士
    0.53
    Lycodon
    0.48
     distanciation
    0.46
     bhakti
    0.46
     polypes
    0.46
     emphasises
    0.45
     enthalpies
    0.45
     splendour
    0.45
    thati
    0.44
    ujjati
    0.44
    POSITIVE LOGITS
     and
    0.54
    ,
    0.50
    as
    0.49
     Performance
    0.46
     Natural
    0.46
    al
    0.44
    C
    0.44
     F
    0.43
     Manufacturing
    0.42
     Energy
    0.42
    Act Density 0.000%

    No Known Activations