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

    Neuronpedia

    INDEX
    Explanations

    prioritize or vote

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     محاضرات
    0.40
     conjecture
    0.38
     seminar
    0.38
    সারণ
    0.36
    <unused59>
    0.36
    opers
    0.36
     दृष्ट
    0.35
    imetric
    0.35
    mitters
    0.35
    myth
    0.35
    POSITIVE LOGITS
     yuan
    0.42
     Tap
    0.40
     আর্থিক
    0.40
     priorit
    0.40
     Jaz
    0.40
     prioritize
    0.39
     failing
    0.39
    Lai
    0.39
     Likewise
    0.38
     lam
    0.38
    Act Density 0.011%

    No Known Activations