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

    Neuronpedia

    INDEX
    Explanations

    prior research and studies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     преду
    0.41
    asında
    0.39
    Episode
    0.39
    BuildActionEntry
    0.36
     подня
    0.36
    用户的
    0.35
    adaş
    0.35
     смогут
    0.35
    érios
    0.34
    hopefully
    0.34
    POSITIVE LOGITS
     studies
    1.73
     research
    1.61
    研究
    1.56
     researches
    1.54
     researchers
    1.52
     исследований
    1.49
     исследования
    1.42
     연구
    1.41
    studies
    1.39
     Studies
    1.38
    Act Density 0.027%

    No Known Activations