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

    Neuronpedia

    INDEX
    Explanations

    simply stating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    0.53
    t
    0.50
    ve
    0.50
    nim
    0.49
    nm
    0.48
    directory
    0.47
    five
    0.47
    nas
    0.47
    names
    0.46
    channel
    0.46
    POSITIVE LOGITS
    槑
    0.50
    走行
    0.49
    粹
    0.46
    BURSE
    0.45
    需要在
    0.44
    东南
    0.44
    ньо
    0.43
    נן
    0.43
    ggel
    0.43
     প্রেসিডেন্টের
    0.43
    Act Density 0.038%

    No Known Activations