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

    Neuronpedia

    INDEX
    Explanations

    article

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suburbs
    -0.08
    渗
    -0.07
     IS
    -0.07
    涉嫌
    -0.07
     obey
    -0.07
    延伸
    -0.07
    往
    -0.06
    省级
    -0.06
    "net
    -0.06
     manage
    -0.06
    POSITIVE LOGITS
    -cover
    0.07
    心思
    0.07
     Thing
    0.07
     Pawn
    0.07
    루
    0.07
    一本
    0.07
    DataContract
    0.06
    NEWS
    0.06
    קל
    0.06
    꿨
    0.06
    Act Density 0.019%

    No Known Activations