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

    Neuronpedia

    INDEX
    Explanations

    list markdown and code formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الأولى
    0.48
     trakt
    0.48
     narr
    0.46
    众多
    0.46
    ב
    0.45
    โ
    0.45
    Narr
    0.44
    Rewarded
    0.44
    奖励
    0.42
    ព័ន្ធ
    0.42
    POSITIVE LOGITS
     चें
    0.47
     Anaheim
    0.46
     Watertown
    0.46
    fromi
    0.44
     Tampa
    0.44
     Jacksonville
    0.42
     Utica
    0.42
     same
    0.41
     Tukey
    0.41
    }$=
    0.41
    Act Density 0.013%

    No Known Activations