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

    Neuronpedia

    INDEX
    Explanations

    URLs and domain names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.60
    ت
    0.50
    त
    0.46
    g
    0.46
    a
    0.45
    el
    0.45
    y
    0.43
    z
    0.42
    tdd
    0.42
    tj
    0.41
    POSITIVE LOGITS
    (
    0.57
     be
    0.42
    Está
    0.38
    </td>
    0.37
    ates
    0.36
    ции
    0.35
    是
    0.35
     podían
    0.35
    ется
    0.34
     podrían
    0.34
    Act Density 0.982%

    No Known Activations