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

    Neuronpedia

    INDEX
    Explanations

    virtual environment setup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ईमित्र
    0.41
    ائیگی
    0.40
     زینت
    0.39
     druż
    0.39
     वेडिंग
    0.39
    สรร
    0.39
    inental
    0.38
    紺
    0.37
    桫
    0.36
     متعلقه
    0.36
    POSITIVE LOGITS
     screenings
    0.37
    ET
    0.36
     lists
    0.36
    Technology
    0.35
    bele
    0.35
    Lists
    0.35
    technology
    0.34
     Lists
    0.34
    lists
    0.34
    ED
    0.33
    Act Density 0.000%

    No Known Activations