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

    Neuronpedia

    INDEX
    Explanations

    special characters and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    as
    0.50
    i
    0.49
    dan
    0.46
    ad
    0.46
    os
    0.46
    x
    0.46
    and
    0.45
    w
    0.44
    ve
    0.42
    ut
    0.42
    POSITIVE LOGITS
    滤波器
    0.45
    行为
    0.45
     生命周期
    0.44
    频道
    0.43
    华为
    0.42
     symbolName
    0.42
    手游
    0.42
    ℡
    0.42
    灵魂
    0.41
    车型
    0.41
    Act Density 0.001%

    No Known Activations