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

    Neuronpedia

    INDEX
    Explanations

    reasoning and classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಯಾವುದೇ
    0.58
    これから
    0.53
     കത്തി
    0.49
    ભગ
    0.48
     любом
    0.48
     වශයෙන්
    0.48
     وخت
    0.48
    ಡುವುದ
    0.47
     మీరు
    0.47
     딱
    0.47
    POSITIVE LOGITS
    x
    0.53
    v
    0.53
    .
    0.50
    시
    0.47
    The
    0.47
    the
    0.47
    ne
    0.46
    This
    0.46
    sim
    0.45
    P
    0.44
    Act Density 0.001%

    No Known Activations