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

    Neuronpedia

    INDEX
    Explanations

    detailed content sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਾ
    0.58
    先生
    0.50
    harmed
    0.49
    ਾਨੂੰ
    0.48
    できない
    0.48
     ਲਈ
    0.46
    𝗮
    0.46
    ሉ
    0.45
    criminals
    0.45
    TikTok
    0.44
    POSITIVE LOGITS
     personal
    0.49
     rigorous
    0.46
     copious
    0.46
     Contents
    0.46
     Indic
    0.44
     “
    0.43
     rigorously
    0.43
     prepar
    0.43
     Suite
    0.42
     내용
    0.42
    Act Density 0.032%

    No Known Activations