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

    Neuronpedia

    INDEX
    Explanations

    to the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     are
    0.82
    ка
    0.73
    ك
    0.66
     তিনি
    0.65
    হ
    0.61
     at
    0.60
    ক
    0.59
     evade
    0.57
     exist
    0.57
    お届け
    0.57
    POSITIVE LOGITS
    ul
    1.01
    3
    0.97
    i
    0.87
    os
    0.87
    the
    0.85
    y
    0.76
    o
    0.73
    ни
    0.70
    am
    0.68
    ere
    0.68
    Act Density 0.002%

    No Known Activations