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

    Neuronpedia

    INDEX
    Explanations

    word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     was
    0.89
     on
    0.84
     to
    0.77
     is
    0.69
     Lý
    0.62
    ሽታ
    0.59
     de
    0.59
     respirator
    0.59
     from
    0.57
     సీ
    0.57
    POSITIVE LOGITS
    <0x80>
    0.64
    و
    0.63
    larının
    0.56
    вер
    0.55
    мого
    0.54
    )\
    0.51
    0
    0.50
     사용하여
    0.49
    iiii
    0.49
    いますが
    0.48
    Act Density 0.227%

    No Known Activations