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

    Neuronpedia

    INDEX
    Explanations

    textbook and its context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ätten
    1.00
    aap
    0.98
     étapes
    0.96
     얘가
    0.94
    ✬
    0.93
     synthèse
    0.92
     éto
    0.91
     član
    0.91
     nối
    0.91
    তনের
    0.89
    POSITIVE LOGITS
    ו
    0.88
    </a>
    0.78
     point
    0.77
     phantom
    0.75
    theo
    0.74
     happiness
    0.73
     pairings
    0.73
     Paradox
    0.73
    </h2>
    0.73
     curve
    0.72
    Act Density 0.002%

    No Known Activations