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

    Neuronpedia

    INDEX
    Explanations

    Chinese and other languages conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ায়
    1.23
     Shortly
    0.96
    داً
    0.95
    وك
    0.94
    forceable
    0.93
     obstructing
    0.92
    بت
    0.91
    vá
    0.89
    yim
    0.89
    ل
    0.88
    POSITIVE LOGITS
    Altri
    1.09
     случаи
    1.07
    d
    1.05
    ă
    1.05
     cria
    1.03
     частиц
    1.03
    ం
    1.02
     이름을
    1.01
    了
    1.01
     naam
    1.00
    Act Density 0.000%

    No Known Activations