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

    Neuronpedia

    INDEX
    Explanations

    Molly Grue, vacuuming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    planet
    0.37
     благо
    0.37
    SUCCESS
    0.37
    owsky
    0.37
    риди
    0.36
    chuk
    0.36
    amaks
    0.36
     dusted
    0.35
     वाइ
    0.35
     changeable
    0.35
    POSITIVE LOGITS
     노동
    0.40
    جي
    0.39
    Jimmy
    0.38
     йөкләү
    0.38
    യായി
    0.38
    dear
    0.37
     Jimmy
    0.37
    래
    0.36
     लीटर
    0.36
    タイミング
    0.36
    Act Density 0.001%

    No Known Activations