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

    Neuronpedia

    INDEX
    Explanations

    companion animals and devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    接着
    0.41
    最后
    0.39
     мыш
    0.38
     avoiding
    0.37
    σ
    0.37
    Chan
    0.36
    士兵
    0.36
    阐
    0.36
     abandoning
    0.36
     recogida
    0.36
    POSITIVE LOGITS
    utable
    0.44
     Вам
    0.44
     Поли
    0.43
     holder
    0.39
    putable
    0.39
     Tope
    0.39
    WhiteBalance
    0.38
     कम्प
    0.38
     компа
    0.38
    굼
    0.37
    Act Density 0.000%

    No Known Activations