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

    Neuronpedia

    INDEX
    Explanations

    gemma, jellyfin, tamu, nolo, hugging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ০
    1.78
    y
    1.77
    t
    1.71
    ل
    1.63
    l
    1.58
    u
    1.55
    ي
    1.51
    ת
    1.50
    ം
    1.49
    ر
    1.49
    POSITIVE LOGITS
    которые
    1.11
    spapers
    1.05
    обходимо
    0.94
    了一个
    0.90
    смотря
    0.88
    了一
    0.87
    ocuk
    0.86
    了一個
    0.86
    ocurrency
    0.84
    了一些
    0.84
    Act Density 0.297%

    No Known Activations