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

    Neuronpedia

    INDEX
    Explanations

    possibility or potential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Can
    1.52
     Can
    1.28
    can
    1.14
    CAN
    1.13
    kan
    1.00
     했습니다
    0.89
    하였습니다
    0.88
    cans
    0.85
    します
    0.83
     합니다
    0.82
    POSITIVE LOGITS
     might
    4.35
     potrebbe
    3.93
    might
    3.87
     could
    3.84
     podría
    3.83
     pourrait
    3.82
     Might
    3.54
     podrían
    3.51
     potrebbero
    3.50
     pourraient
    3.49
    Act Density 0.921%

    No Known Activations