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

    Neuronpedia

    INDEX
    Explanations

    legal concept of tort

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aniti
    0.82
    et
    0.79
    ar
    0.74
    ores
    0.73
    an
    0.72
    anel
    0.71
    arza
    0.69
    த்தனர்
    0.68
    ep
    0.67
    ey
    0.67
    POSITIVE LOGITS
    ↵↵
    0.94
    :
    0.83
     наш
    0.76
     είναι
    0.74
     bunların
    0.74
    是我们
    0.72
     noastră
    0.72
    则是
    0.70
    м
    0.70
     новий
    0.70
    Act Density 0.001%

    No Known Activations