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

    Neuronpedia

    INDEX
    Explanations

    alertness and attention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    0.90
    ల
    0.86
     furo
    0.81
     Neuer
    0.80
    ס
    0.75
     armband
    0.75
    t
    0.75
     aerob
    0.73
     arme
    0.73
    ీ
    0.72
    POSITIVE LOGITS
    де
    0.83
    ිබ
    0.83
     кушымта
    0.78
    друг
    0.77
    Prix
    0.75
    ⅽ
    0.74
    ்து
    0.73
    grams
    0.72
    дачи
    0.72
    ᱓
    0.72
    Act Density 0.004%

    No Known Activations