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

    Neuronpedia

    INDEX
    Explanations

    vapor upwards, liquid downwards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    стве
    0.49
     नवरा
    0.45
    miR
    0.44
    кана
    0.44
    c
    0.44
    ما
    0.43
    μάτων
    0.43
    ფორ
    0.42
    ए
    0.42
    дент
    0.42
    POSITIVE LOGITS
     personalità
    0.46
    ;";
    0.43
    padding
    0.42
     উঠিয়া
    0.42
    elite
    0.41
    wireless
    0.40
    ہوری
    0.40
     ঘুম
    0.40
     pah
    0.39
    ujete
    0.39
    Act Density 0.000%

    No Known Activations