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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.94
    aining
    0.72
     vegetal
    0.72
    H
    0.72
     pug
    0.71
    P
    0.71
     waist
    0.70
    unden
    0.70
     থাকুন
    0.69
    nth
    0.68
    POSITIVE LOGITS
    ק
    0.93
    るので
    0.90
    ی
    0.89
     innebär
    0.86
     Tổng
    0.85
     Interfaith
    0.85
    ä
    0.85
    edLeft
    0.84
     MCQ
    0.84
     Tập
    0.83
    Act Density 0.003%

    No Known Activations