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

    Neuronpedia

    INDEX
    Explanations

    contrast and continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     весьма
    0.48
     ಬಹಳ
    0.44
     remarquable
    0.43
    лянчук
    0.43
     veoma
    0.42
    ਰੇ
    0.42
     verfügbar
    0.41
     velmi
    0.41
     sucesivamente
    0.41
    いくつかの
    0.41
    POSITIVE LOGITS
     Beyoncé
    0.47
     când
    0.46
     endometriosis
    0.43
     αλλά
    0.42
    结束后
    0.42
    ihanna
    0.41
     Beyonce
    0.41
    但是在
    0.40
     ketchup
    0.40
    ciąż
    0.40
    Act Density 0.008%

    No Known Activations