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

    Neuronpedia

    INDEX
    Explanations

    Okay, prediction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    angkap
    0.55
     അതു
    0.52
     أبر
    0.50
     አስተ
    0.50
    បញ្ចូល
    0.49
    oki
    0.48
    采
    0.48
    钣
    0.48
    讴
    0.47
     ተመሳሳይ
    0.47
    POSITIVE LOGITS
     making
    0.43
     fatigue
    0.41
     notebooks
    0.41
     cozinha
    0.40
    0.40
     expiry
    0.39
     liquidity
    0.39
     chairmanship
    0.39
     duration
    0.38
    bage
    0.38
    Act Density 0.000%

    No Known Activations