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

    Neuronpedia

    INDEX
    Explanations

    locations and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    view
    0.45
     приз
    0.42
     Weighted
    0.40
     효과
    0.39
     ensues
    0.38
    forder
    0.38
     viết
    0.38
     view
    0.37
     efectu
    0.36
    zy
    0.36
    POSITIVE LOGITS
     guerras
    0.39
     combinations
    0.38
     fates
    0.38
    uric
    0.37
     dxc
    0.37
    ServerSocket
    0.37
     dunes
    0.36
    芫
    0.36
     +#
    0.36
     سمت
    0.36
    Act Density 0.000%

    No Known Activations