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

    Neuronpedia

    INDEX
    Explanations

    legal and cultural contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    feitos
    0.45
    لڈ
    0.40
     modalidades
    0.40
    ávat
    0.40
    новый
    0.40
     accolade
    0.39
     levy
    0.39
    ловой
    0.39
    precio
    0.38
     পরিমান
    0.38
    POSITIVE LOGITS
     whose
    0.73
     which
    0.57
    which
    0.57
    whose
    0.57
     cuyo
    0.53
     Whose
    0.49
     и
    0.48
    ซึ่ง
    0.48
     *,
    0.47
     ,
    0.47
    Act Density 0.001%

    No Known Activations