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

    Neuronpedia

    INDEX
    Explanations

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     partielle
    0.61
     Vestone
    0.56
     gejala
    0.47
     paio
    0.47
     restit
    0.46
    ⠀
    0.46
    0.46
    รือ
    0.46
    стати
    0.46
    ➥
    0.45
    POSITIVE LOGITS
    有着
    0.57
    を有
    0.55
    ında
    0.54
    ının
    0.53
    тые
    0.50
    Пу
    0.50
    的工作
    0.49
    不上
    0.49
    órica
    0.48
     않아
    0.48
    Act Density 0.054%

    No Known Activations