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

    Neuronpedia

    INDEX
    Explanations

    harmful, gravity, harm, focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    רו
    0.53
     звезд
    0.50
    шением
    0.48
     нако
    0.47
    рисо
    0.47
    ப்பத
    0.46
     मिळाल
    0.46
     accumulated
    0.46
     retrait
    0.45
     تحصل
    0.44
    POSITIVE LOGITS
     Flipkart
    0.42
    া
    0.41
    ('/:
    0.41
    Favorites
    0.40
    เลต
    0.40
     اے
    0.40
    加快
    0.40
    hty
    0.40
    展开
    0.40
    a
    0.40
    Act Density 0.001%

    No Known Activations