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

    Neuronpedia

    INDEX
    Explanations

    ordering from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tı
    1.00
    یە
    0.82
     bien
    0.81
    ti
    0.79
    t
    0.78
     well
    0.77
    ný
    0.76
    POL
    0.74
    ности
    0.73
    ти
    0.71
    POSITIVE LOGITS
    ững
    0.81
     daarbij
    0.79
    ayanti
    0.77
    Ꭽ
    0.77
     যাওয়ার
    0.77
    டுவத
    0.75
    aying
    0.75
    ଝ
    0.75
    ádiz
    0.75
    トゥーン
    0.75
    Act Density 0.000%

    No Known Activations