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

    Neuronpedia

    INDEX
    Explanations

    list item introducers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ம்
    0.62
    ться
    0.55
    л
    0.55
    ਾ
    0.53
     pretence
    0.52
    ة
    0.51
    या
    0.48
    ′
    0.46
    anath
    0.46
    ście
    0.45
    POSITIVE LOGITS
    ন
    0.63
    uleiro
    0.61
    sti
    0.60
    shortest
    0.57
    น้ำ
    0.56
    ش
    0.56
    rb
    0.54
    től
    0.54
    self
    0.54
    là
    0.54
    Act Density 2.019%

    No Known Activations