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

    Neuronpedia

    INDEX
    Explanations

    about [concept]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     аналоги
    0.48
    精准
    0.42
     составля
    0.42
     всегда
    0.42
    ことも
    0.41
    Amazing
    0.41
    वेळी
    0.41
     всему
    0.41
    nalia
    0.41
    重启
    0.41
    POSITIVE LOGITS
     hỏi
    0.42
     porod
    0.42
     Ph
    0.41
     Hospital
    0.40
     Number
    0.39
     haces
    0.39
     Post
    0.39
     preguntó
    0.38
     Herm
    0.38
     Social
    0.38
    Act Density 0.001%

    No Known Activations