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

    Neuronpedia

    INDEX
    Explanations

    inner light or inspiration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     сообщи
    0.47
     ск
    0.44
    ный
    0.43
     меры
    0.43
     проекты
    0.43
     проек
    0.42
    та
    0.42
     значит
    0.42
    чках
    0.42
     хотят
    0.40
    POSITIVE LOGITS
    CLUSTERED
    0.49
     nei
    0.48
     heller
    0.47
     Asst
    0.47
    šky
    0.46
    حيان
    0.46
     Humor
    0.46
     Astral
    0.46
    unger
    0.45
     cayenne
    0.44
    Act Density 0.001%

    No Known Activations