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

    Neuronpedia

    INDEX
    Explanations

    introvert

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ع
    0.71
    S
    0.63
    U
    0.60
    ла
    0.59
    ड
    0.55
    이를
    0.52
    ون
    0.50
    ا
    0.50
    ت
    0.50
    ด
    0.50
    POSITIVE LOGITS
     introvert
    0.59
     manifesto
    0.54
     পেয়ে
    0.50
     extro
    0.49
     foreclosure
    0.48
     personalities
    0.47
     GENER
    0.47
     capitalists
    0.47
    cluso
    0.46
     ECS
    0.46
    Act Density 0.007%

    No Known Activations