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

    Neuronpedia

    INDEX
    Explanations

    anatomy and mutilation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    亼
    1.64
     extinguishers
    1.53
     maraming
    1.49
     bookcases
    1.48
    멩
    1.48
     harapan
    1.47
    ইহার
    1.45
    深
    1.44
    条件
    1.43
    公安
    1.43
    POSITIVE LOGITS
    ী
    2.59
    на
    2.22
    ER
    2.14
    та
    2.11
    ية
    1.91
    ных
    1.88
    u
    1.87
    ım
    1.84
    ında
    1.83
    ین
    1.82
    Act Density 0.074%

    No Known Activations