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

    Neuronpedia

    INDEX
    Explanations

    filling gaps or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <.
    0.49
    𝐭
    0.47
    ()\
    0.45
    ն
    0.45
    <\
    0.44
    )}_{\
    0.44
     pharmaceuticals
    0.43
     доку
    0.42
    (<
    0.41
     phía
    0.41
    POSITIVE LOGITS
    Κ
    0.49
    Alg
    0.49
    ud
    0.47
    these
    0.46
    UEFA
    0.46
    ۰
    0.46
    am
    0.46
    ຮ
    0.46
    Sixth
    0.45
     پیشنه
    0.45
    Act Density 0.002%

    No Known Activations