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

    Neuronpedia

    INDEX
    Explanations

    pages, journal, parent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    im
    0.88
    zoni
    0.80
    ud
    0.71
    jones
    0.70
    ur
    0.68
     डिप्ट
    0.68
    ovati
    0.67
    虑
    0.67
    vest
    0.66
    ಡುವುದ
    0.66
    POSITIVE LOGITS
     утром
    0.84
     fizer
    0.77
    ↵
    0.75
     ア
    0.72
     ワ
    0.70
     enzyme
    0.70
     opacity
    0.70
     இரவு
    0.67
    र्तन
    0.67
     esoteric
    0.67
    Act Density 0.004%

    No Known Activations