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

    Neuronpedia

    INDEX
    Explanations

    numbered or bulleted lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nonumber
    0.38
     unworthy
    0.36
     όχι
    0.36
     ikke
    0.35
     hilfreich
    0.35
     falso
    0.34
     není
    0.34
     nejsou
    0.33
     இல்லாத
    0.33
     falsehood
    0.33
    POSITIVE LOGITS
     затем
    0.53
     then
    0.43
     prepare
    0.43
     Затем
    0.41
    调整
    0.40
     następnie
    0.40
    然后
    0.39
     przygot
    0.39
     vervolgens
    0.39
     tweaked
    0.39
    Act Density 0.336%

    No Known Activations