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

    Neuronpedia

    INDEX
    Explanations

    explicitly considering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鐧
    0.45
    णाल
    0.44
     pasal
    0.44
    埚
    0.43
    殡
    0.43
    ᐋ
    0.43
    사랑
    0.41
     geographies
    0.41
    昛
    0.41
    峴
    0.41
    POSITIVE LOGITS
    0.59
     vivid
    0.56
     firstly
    0.55
    0.50
     meanwhile
    0.47
    （
    0.47
     comprehensively
    0.46
    Compared
    0.46
    ——
    0.45
    ¡
    0.44
    Act Density 0.018%

    No Known Activations