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

    Neuronpedia

    INDEX
    Explanations

    Gemma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াভাবিক
    0.41
    ঠোর
    0.41
     احساس
    0.39
    \}$,
    0.39
     obsess
    0.37
    이니까
    0.37
     अंध
    0.37
    ውነ
    0.37
     често
    0.36
    स्करी
    0.36
    POSITIVE LOGITS
     ஆகிய
    0.51
    ຂອງທ່ານ
    0.48
    ﺎ
    0.47
     sebuah
    0.46
     plugin
    0.45
     вашего
    0.45
     आपके
    0.44
     مؤرشف
    0.44
    েল
    0.43
    つの
    0.43
    Act Density 0.002%

    No Known Activations