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

    Neuronpedia

    INDEX
    Explanations

    health concerns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     velcro
    0.41
    ༨
    0.39
     elution
    0.38
     ልዩ
    0.37
    ಜನ
    0.37
     উপসং
    0.37
    ඇ
    0.37
    ংখ্যান
    0.36
     lỗ
    0.36
     स्थाई
    0.35
    POSITIVE LOGITS
     tri
    0.41
    Concern
    0.38
     Concern
    0.37
     concern
    0.35
    мор
    0.34
     disadvantage
    0.34
    дем
    0.34
     NZ
    0.33
    ↵
    0.32
     obligation
    0.32
    Act Density 0.001%

    No Known Activations