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

    Neuronpedia

    INDEX
    Explanations

    rewards for contributions and achievements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     জানালেন
    0.72
     gyda
    0.71
    analyzer
    0.69
     fascinated
    0.68
     Laws
    0.68
     Facilities
    0.66
     équipé
    0.65
     নিয়েই
    0.64
     terbatas
    0.64
     Regulations
    0.64
    POSITIVE LOGITS
     contributions
    2.16
     contribution
    2.03
     Contribution
    1.80
    contribution
    1.80
     Contributions
    1.74
    贡献
    1.70
     meritorious
    1.63
     accomplishments
    1.63
     achievements
    1.61
    貢献
    1.59
    Act Density 0.159%

    No Known Activations