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

    Neuronpedia

    INDEX
    Explanations

    variable assignment and unpacking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     少し
    0.43
    柣
    0.43
     ermög
    0.41
    の上に
    0.41
    专注
    0.41
    ですし
    0.41
    接触
    0.40
     እስከ
    0.40
    噜
    0.40
    穗
    0.39
    POSITIVE LOGITS
     _,
    0.77
    _,
    0.58
     _)
    0.57
    (_,
    0.55
     are
    0.55
    (_)
    0.51
     ஆகிய
    0.50
     were
    0.48
    ,_
    0.48
     _
    0.47
    Act Density 0.008%

    No Known Activations