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

    Neuronpedia

    INDEX
    Explanations

    dual boot, bags, value, caution, held, ridge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ás
    0.54
    ne
    0.47
    ác
    0.46
    ób
    0.45
    lui
    0.45
    头
    0.45
    ū
    0.44
    te
    0.44
    ūt
    0.43
    总部
    0.42
    POSITIVE LOGITS
    Cast
    0.50
    rangea
    0.48
    CubeSize
    0.48
     burrito
    0.47
     geopol
    0.47
    attled
    0.47
    Antaeotricha
    0.47
     chauffage
    0.46
     chorizo
    0.46
     IUCN
    0.45
    Act Density 0.000%

    No Known Activations