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

    Neuronpedia

    INDEX
    Explanations

    ough / ought / ugh

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     यदि
    0.42
     Ancak
    0.42
     গুরুদেব
    0.41
    rico
    0.41
     Chica
    0.40
     બાબ
    0.40
    ្ស
    0.39
     jika
    0.39
     편리
    0.38
     Однако
    0.38
    POSITIVE LOGITS
    ough
    1.70
    ought
    1.58
    OUGH
    1.57
     tough
    1.49
     ought
    1.46
    ught
    1.44
     Tough
    1.44
    ugh
    1.43
     Hugh
    1.42
    tough
    1.42
    Act Density 0.040%

    No Known Activations