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

    Neuronpedia

    INDEX
    Explanations

    reservation or cost

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diamètre
    0.41
    Select
    0.39
     생활
    0.39
     ተጨማሪ
    0.39
     antig
    0.38
     slight
    0.38
    އް
    0.38
    에서의
    0.38
    தில்
    0.37
    odim
    0.37
    POSITIVE LOGITS
    但我
    0.47
    တို့ကို
    0.41
    itmen
    0.37
    ጅም
    0.36
    tke
    0.36
    experiments
    0.35
     pertence
    0.34
     예약
    0.34
    予約
    0.34
    但是我
    0.34
    Act Density 0.000%

    No Known Activations