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

    Neuronpedia

    INDEX
    Explanations

    manufacturing units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     なさい
    0.52
    0.49
     অবজারভার
    0.49
    arkeit
    0.49
     正規
    0.49
     選
    0.49
     טור
    0.49
     世界
    0.48
     weeding
    0.48
     椅
    0.48
    POSITIVE LOGITS
    க்கு
    0.50
    OK
    0.50
    Cool
    0.46
    AAA
    0.46
     cool
    0.44
    My
    0.44
    AAAA
    0.43
    علي
    0.43
    冷
    0.43
    Ok
    0.43
    Act Density 0.013%

    No Known Activations