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

    Neuronpedia

    INDEX
    Explanations

    poses risk as deadly as smoking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ক্ষণের
    0.53
    ྣ
    0.49
    เขียน
    0.48
     लिखिए
    0.48
     positrons
    0.47
    ྗ
    0.47
     Assumptions
    0.46
     ფუნქ
    0.46
    ក្រោម
    0.46
     illustrazione
    0.45
    POSITIVE LOGITS
    0.53
    confidence
    0.40
    tra
    0.40
    ayers
    0.39
    ky
    0.38
    тя
    0.38
    to
    0.38
     był
    0.37
    sku
    0.37
     hạn
    0.37
    Act Density 0.000%

    No Known Activations