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

    Neuronpedia

    INDEX
    Explanations

    schemes, flags, purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وإ
    0.41
     Usted
    0.41
    voll
    0.41
    이며
    0.40
    गोर
    0.40
     hermoso
    0.40
     Rub
    0.39
    이고
    0.39
     важное
    0.39
     artificial
    0.39
    POSITIVE LOGITS
    chaoxing
    0.52
    ₀
    0.50
     Eurasia
    0.47
    ｀)
    0.47
    atürk
    0.46
    abhavo
    0.46
    ÕES
    0.46
     バー
    0.45
     desk
    0.45
    rede
    0.45
    Act Density 0.000%

    No Known Activations