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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     প্রাণে
    0.34
    ाइवेट
    0.32
    Gli
    0.32
    Flicky
    0.32
    ట్స్‌
    0.31
    ktCap
    0.31
    ruktur
    0.30
    kül
    0.30
    ஜ்மஹ
    0.30
    asionally
    0.30
    POSITIVE LOGITS
     Ad
    0.33
    ↵
    0.31
     Australia
    0.29
     AST
    0.29
     in
    0.29
    m
    0.29
     New
    0.28
     In
    0.28
     IN
    0.28
     N
    0.28
    Act Density 0.040%

    No Known Activations