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

    Neuronpedia

    INDEX
    Explanations

    business problem-solving and marketing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    с
    0.69
    し
    0.47
    斯
    0.45
    它
    0.44
    س
    0.44
    다
    0.41
    槸
    0.40
    文化
    0.40
    ۳
    0.40
    টি
    0.39
    POSITIVE LOGITS
    is
    0.66
    il
    0.64
    ad
    0.59
    ting
    0.56
    -
    0.53
    ir
    0.53
     a
    0.52
    x
    0.52
     exuber
    0.50
    isst
    0.49
    Act Density 0.513%

    No Known Activations