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

    Neuronpedia

    INDEX
    Explanations

    mechanical methods and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    和
    0.31
     assets
    0.30
     እና
    0.29
     Assets
    0.29
     upkeep
    0.29
    ियर्स
    0.29
    德
    0.29
     creditors
    0.29
     contestants
    0.29
     repurchase
    0.29
    POSITIVE LOGITS
    방법
    0.36
    的过程中
    0.32
     или
    0.32
     طریقے
    0.32
    或其他
    0.31
    贮
    0.31
     কিংবা
    0.30
     teknologi
    0.30
    测量
    0.30
     sexu
    0.30
    Act Density 0.000%

    No Known Activations