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

    Neuronpedia

    INDEX
    Explanations

    even to try or ask

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wię
    0.71
     واپسی
    0.71
    さま
    0.71
    ారా
    0.70
     दब
    0.70
    勢
    0.70
    ុំ
    0.69
     receding
    0.68
    प्रभाव
    0.68
    サスカ
    0.66
    POSITIVE LOGITS
     even
    3.61
    even
    3.36
     Even
    3.17
    Even
    3.10
     даже
    2.92
     навіть
    2.78
     EVEN
    2.70
     bahkan
    2.63
     siquiera
    2.58
     nawet
    2.40
    Act Density 0.199%

    No Known Activations