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

    Neuronpedia

    INDEX
    Explanations

    code examples and formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ంద
    1.46
    ে
    1.39
    ా
    1.30
    ی
    1.25
    ೆ
    1.23
    ره
    1.22
    lst
    1.21
    ISM
    1.20
    они
    1.20
     sparkles
    1.20
    POSITIVE LOGITS
    िक
    2.38
    ار
    1.83
    ar
    1.79
    りの
    1.76
     hängt
    1.65
    šku
    1.62
    ak
    1.61
     länge
    1.58
    ق
    1.56
    یں
    1.55
    Act Density 0.576%

    No Known Activations