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

    Neuronpedia

    INDEX
    Explanations

    give me you requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.25
    {//
    1.11
    بي
    1.09
    ار
    1.01
    ។
    0.99
    ৩৩
    0.97
    وم
    0.95
    ৩৭
    0.95
    প্রায়
    0.95
     adhipp
    0.95
    POSITIVE LOGITS
    ’
    1.59
    '
    1.26
     and
    1.20
    v
    1.04
    "
    1.02
    ր
    1.01
    has
    0.99
    ी
    0.98
    ι
    0.96
     Give
    0.95
    Act Density 0.225%

    No Known Activations