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

    Neuronpedia

    INDEX
    Explanations

    programming code and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Struct
    0.48
     BasicContainer
    0.48
     Resol
    0.46
     IncludeField
    0.46
     Strukt
    0.46
     İstifadə
    0.45
     изоли
    0.45
    婍
    0.45
     RasterModelGrid
    0.44
     сило
    0.44
    POSITIVE LOGITS
    challenged
    0.53
     botched
    0.52
    vertices
    0.51
    cher
    0.49
    ystems
    0.49
    ver
    0.48
     regimes
    0.48
    ben
    0.47
    ensively
    0.47
    label
    0.46
    Act Density 0.003%

    No Known Activations