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

    Neuronpedia

    INDEX
    Explanations

    . sentence / sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Người
    0.80
     Союз
    0.77
     Karten
    0.75
     കണ്ട
    0.74
     രാജ്യ
    0.73
    izace
    0.73
    িশ
    0.72
    वारीत
    0.71
    elat
    0.71
    登場
    0.70
    POSITIVE LOGITS
    timer
    0.73
    lonitrile
    0.71
    ㄱ
    0.70
    .”.
    0.70
     പ്രതിഷേധ
    0.69
    ත්වය
    0.69
    !”.
    0.68
    ուն
    0.68
    guards
    0.67
    achev
    0.67
    Act Density 0.071%

    No Known Activations