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

    Neuronpedia

    INDEX
    Explanations

    intrusive thoughts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Oss
    0.76
    ót
    0.67
     International
    0.66
    OI
    0.65
     अंतर्राष्ट्रीय
    0.62
    اون
    0.61
    International
    0.61
     मानवता
    0.60
     tarda
    0.60
    umat
    0.60
    POSITIVE LOGITS
    ✵
    0.71
    ➢
    0.68
    Attributes
    0.68
    ເພດ
    0.67
     स्टूडेंट
    0.66
    apkan
    0.64
    يران
    0.62
    觚
    0.62
    Cory
    0.62
    Всім
    0.62
    Act Density 0.008%

    No Known Activations