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

    Neuronpedia

    INDEX
    Explanations

    but and contrast, foreign equivalents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     więc
    0.54
    所以
    0.48
     그러니까
    0.47
     donc
    0.45
     jadi
    0.44
    つまり
    0.44
     dunque
    0.44
     Jadi
    0.44
     yep
    0.43
     tehát
    0.43
    POSITIVE LOGITS
     nevertheless
    1.01
     dennoch
    1.00
     néanmoins
    0.95
     tuttavia
    0.91
     however
    0.89
    Nevertheless
    0.89
     azonban
    0.87
     unfortunately
    0.84
     Nevertheless
    0.84
     όμως
    0.84
    Act Density 0.004%

    No Known Activations