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

    Neuronpedia

    INDEX
    Explanations

    As a large language model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ம்பிய
    0.39
    噤
    0.37
     뜻
    0.37
    ALTERNATIVNAMEN
    0.36
     بیا
    0.35
     vento
    0.35
     weakest
    0.34
    ที่สุด
    0.34
     trazer
    0.34
     compléter
    0.34
    POSITIVE LOGITS
     알
    0.42
    ⁀
    0.42
    Tout
    0.40
    وتن
    0.40
    walkers
    0.40
     rebus
    0.40
     Charcoal
    0.40
    argeon
    0.39
     ভার্চ
    0.39
    アル
    0.38
    Act Density 0.001%

    No Known Activations