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

    Neuronpedia

    INDEX
    Explanations

    identify opportunities and trends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arche
    0.50
    Olá
    0.46
     om
    0.44
    Silicon
    0.43
    но
    0.43
     dahil
    0.43
     nl
    0.43
    d
    0.43
     n
    0.42
     att
    0.42
    POSITIVE LOGITS
     previewBuilder
    0.48
     spaceShip
    0.47
     sacrific
    0.46
     vasena
    0.45
    .])
    0.44
    شى
    0.44
     माग
    0.44
     பகுதியை
    0.44
    धि
    0.44
    詿
    0.43
    Act Density 0.001%

    No Known Activations