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

    Neuronpedia

    INDEX
    Explanations

    list item separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ರಿನ
    0.48
     a
    0.46
     kilobytes
    0.45
    लेखित
    0.44
     an
    0.43
     THE
    0.43
     सारा
    0.42
     the
    0.41
    值的
    0.40
    atthakath
    0.40
    POSITIVE LOGITS
    0.55
    ?:
    0.54
    ：
    0.50
     =
    0.50
    ":
    0.49
    /
    0.49
    <0xE3>
    0.49
    ’:
    0.47
    則是
    0.47
    ]
    0.44
    Act Density 0.907%

    No Known Activations