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

    Neuronpedia

    INDEX
    Explanations

    while others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    这样一个
    0.99
    खों
    0.86
    সমস্ত
    0.84
    ೊಂದು
    0.83
     రెండు
    0.82
    Apart
    0.82
     Person
    0.81
    除了
    0.80
    ://
    0.79
     के
    0.79
    POSITIVE LOGITS
     others
    5.98
     Others
    5.21
    Others
    5.11
    others
    4.99
     दूसरों
    3.01
     অন্যরা
    2.87
    THERS
    2.79
     অন্যদের
    2.71
    别人
    2.52
     دوسروں
    2.34
    Act Density 0.204%

    No Known Activations