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

    Neuronpedia

    INDEX
    Explanations

    cannot be a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     its
    0.79
     έκ
    0.77
    Its
    0.76
     Its
    0.76
     perforated
    0.75
    将其
    0.74
    its
    0.74
     aşağıdaki
    0.74
     umožňuje
    0.72
     அவர்களின்
    0.72
    POSITIVE LOGITS
     deserts
    0.84
     cannot
    0.82
    可愛い
    0.79
     நிமிடங்கள்
    0.78
    бол
    0.77
     jungles
    0.77
     hardly
    0.77
     happenings
    0.76
     woes
    0.76
     humaines
    0.76
    Act Density 0.012%

    No Known Activations