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

    Neuronpedia

    INDEX
    Explanations

    count "e"s

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     може
    0.54
     тоді
    0.49
     чувства
    0.48
     тогда
    0.48
     ಕೆಲವು
    0.47
     אבל
    0.47
     느끼
    0.47
    pective
    0.46
     많은
    0.44
     परिणाम
    0.43
    POSITIVE LOGITS
     Softball
    0.53
     softball
    0.51
    s
    0.49
    افة
    0.49
     Bicycle
    0.46
     Gravity
    0.44
     baseball
    0.43
    মি
    0.42
    ாரம்
    0.42
     moto
    0.41
    Act Density 0.023%

    No Known Activations