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

    Neuronpedia

    INDEX
    Explanations

    mathematical/code symbols and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     effluents
    0.54
     într
    0.53
    ѓ
    0.51
    <unused675>
    0.51
    จำเป็น
    0.50
     እንዲሁ
    0.50
     аллер
    0.50
    有個
    0.49
    <unused2013>
    0.49
     Επι
    0.48
    POSITIVE LOGITS
    hour
    0.46
    x
    0.45
    berger
    0.44
    ars
    0.44
    ópez
    0.44
    ann
    0.44
    repeat
    0.43
     historical
    0.41
    pic
    0.40
    page
    0.40
    Act Density 0.016%

    No Known Activations