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

    Neuronpedia

    INDEX
    Explanations

    JSON Lines, Origin, Move

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apathy
    0.41
     wür
    0.39
    പ്പ്
    0.39
     മോ
    0.38
    Seems
    0.36
    ाम
    0.36
     embroiled
    0.36
     appellate
    0.36
    コミュニ
    0.35
     tourisme
    0.35
    POSITIVE LOGITS
     Of
    0.43
     коп
    0.42
    <unused234>
    0.41
     убор
    0.39
     And
    0.39
    的话
    0.37
     及
    0.37
     дорогие
    0.36
    Видео
    0.36
    логия
    0.36
    Act Density 0.002%

    No Known Activations