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

    Neuronpedia

    INDEX
    Explanations

    concessions and contrasts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     takže
    0.54
    ។
    0.54
     zodat
    0.54
     ។
    0.50
     wobei
    0.49
     sodass
    0.48
    》。
    0.47
    。
    0.47
     وذلك
    0.45
    "],"
    0.44
    POSITIVE LOGITS
     meanwhile
    0.72
     though
    0.71
     despite
    0.69
     although
    0.69
     unlike
    0.65
     choć
    0.60
     however
    0.59
     iako
    0.59
     aunque
    0.59
     while
    0.58
    Act Density 0.101%

    No Known Activations