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

    Neuronpedia

    INDEX
    Explanations

    Errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    涂料
    -0.07
     Alonso
    -0.07
    Winter
    -0.07
    ่าว
    -0.07
     sorted
    -0.07
     같은
    -0.07
    不属于
    -0.07
     bamboo
    -0.07
     Psr
    -0.07
    スタッ
    -0.07
    POSITIVE LOGITS
     intimidation
    0.07
    不愿意
    0.07
     regimes
    0.07
    ++){
↵
    0.07
     hver
    0.07
    uity
    0.06
    群众
    0.06
    芷
    0.06
     organization
    0.06
    ek
    0.06
    Act Density 0.001%

    No Known Activations