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

    Neuronpedia

    INDEX
    Explanations

    if, conditional, or uncertainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    емости
    0.45
    猪
    0.44
    ul
    0.43
     வெவ்வேறு
    0.42
    кус
    0.41
    getJSON
    0.41
     surn
    0.41
    }>\
    0.40
     பல்வேறு
    0.40
    ต่างๆ
    0.39
    POSITIVE LOGITS
     hvis
    0.49
     اگر
    0.46
     إذا
    0.45
     Якщо
    0.44
    ركه
    0.43
    إذا
    0.43
     اذا
    0.42
     отказаться
    0.42
     אם
    0.42
     tranquila
    0.41
    Act Density 0.004%

    No Known Activations