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

    Neuronpedia

    INDEX
    Explanations

    "We" or "This" starts an explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ер
    0.49
    де
    0.46
    ма
    0.45
    ការ
    0.44
    ރ
    0.43
    ни
    0.41
    ды
    0.41
    ion
    0.40
     послу
    0.39
    нит
    0.39
    POSITIVE LOGITS
    pcl
    0.51
     compds
    0.50
     对于
    0.49
    ᴄ
    0.49
    㣻
    0.48
     Matcha
    0.46
    च्युअल
    0.46
     亻
    0.46
     价
    0.46
     successivement
    0.45
    Act Density 0.874%

    No Known Activations