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

    Neuronpedia

    INDEX
    Explanations

    .jpg

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.54
    n
    0.52
    t
    0.49
    small
    0.48
    tail
    0.48
    var
    0.47
    ergy
    0.46
    osm
    0.44
    warm
    0.42
    after
    0.41
    POSITIVE LOGITS
    🏪
    0.53
     Rojas
    0.52
    кін
    0.52
    ⏫
    0.51
    …………………………………………
    0.50
     തുറ
    0.48
    𝗔
    0.48
    🗯
    0.48
    垀
    0.48
    ⏪
    0.47
    Act Density 0.000%

    No Known Activations