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

    Neuronpedia

    INDEX
    Explanations

    categories of people or things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ारों
    1.34
     борьбы
    1.27
     lor
    1.22
     thirds
    1.18
    +}$
    1.18
     alumin
    1.18
    कभी
    1.17
    机关
    1.11
     Denk
    1.10
     irgendwie
    1.09
    POSITIVE LOGITS
    𝐋
    1.57
    ン
    1.53
    𝐄
    1.50
    ন
    1.47
    دل
    1.47
    traj
    1.46
    jego
    1.44
    nte
    1.44
    ยนต์
    1.43
     gridSize
    1.43
    Act Density 0.157%

    No Known Activations