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

    Neuronpedia

    INDEX
    Explanations

    as it is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जिसका
    0.45
    itatif
    0.41
    要是
    0.37
    于是
    0.37
    <b>
    0.37
    ȱ
    0.36
    Yup
    0.36
    ↵↵↵↵↵↵↵
    0.36
    તમાં
    0.35
    ysel
    0.35
    POSITIVE LOGITS
     because
    0.67
     karena
    0.66
     이는
    0.66
     ஏனெனில்
    0.63
    これは
    0.63
     koska
    0.61
    เพราะ
    0.61
     there
    0.61
    因为
    0.61
     deoarece
    0.59
    Act Density 0.017%

    No Known Activations