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

    Neuronpedia

    INDEX
    Explanations

    internal dialog, still facing, 6th century, conditioner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    離島
    0.55
    Pune
    0.53
    Odds
    0.50
    াধীন
    0.49
     Groove
    0.48
    ‌ترین
    0.47
    ע
    0.47
    CacheV
    0.47
    0
    0.46
    ‌آ
    0.45
    POSITIVE LOGITS
    ethers
    0.48
    typed
    0.47
    r
    0.47
    .
    0.47
    s
    0.47
    rio
    0.46
     혈
    0.45
    េស
    0.45
    sores
    0.45
    med
    0.44
    Act Density 0.000%

    No Known Activations