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

    Neuronpedia

    INDEX
    Explanations

    contrast or concession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Thanks
    0.43
    W
    0.42
    Excellent
    0.42
    تاریخ
    0.42
    situ
    0.42
    Mamm
    0.42
    Adjust
    0.41
    Coin
    0.41
    Induced
    0.41
     তৎকালীন
    0.40
    POSITIVE LOGITS
     αλλά
    0.51
     但
    0.49
    స్తూ
    0.47
     pero
    0.46
     irgendwie
    0.45
     nhưng
    0.45
     lakini
    0.44
     แต่
    0.44
    但也
    0.44
     ngunit
    0.43
    Act Density 0.008%

    No Known Activations