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

    Neuronpedia

    INDEX
    Explanations

    say '*'

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     May
    0.78
     MAY
    0.63
     Del
    0.62
    캔
    0.61
     Merr
    0.61
     credit
    0.60
     ma
    0.60
    IRC
    0.58
    May
    0.57
     legend
    0.57
    POSITIVE LOGITS
    Four
    0.89
    숑
    0.81
    ᓛ
    0.79
     எங்க
    0.79
     پوست
    0.74
     नैतिक
    0.74
     four
    0.71
     Noeud
    0.71
    Artifact
    0.71
    钮
    0.71
    Act Density 0.054%

    No Known Activations