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

    Neuronpedia

    INDEX
    Explanations

    exemplary, different, damages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صنع
    0.41
     Fakt
    0.39
    dal
    0.38
    झ
    0.38
     recetas
    0.37
     fabriqu
    0.37
    जिक
    0.36
    manufact
    0.36
     buyout
    0.36
    theon
    0.36
    POSITIVE LOGITS
    โท
    0.38
    两种
    0.37
    BufferedWriter
    0.37
     кана
    0.36
    Петер
    0.36
     dhammo
    0.36
     quả
    0.36
    两位
    0.35
    }.}
    0.35
    bourg
    0.35
    Act Density 0.004%

    No Known Activations