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

    Neuronpedia

    INDEX
    Explanations

    c# code namespaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Array
    0.75
    Array
    0.68
     ArrayRef
    0.53
     array
    0.51
    配列
    0.50
     ARRAY
    0.45
     Buffer
    0.43
     buffer
    0.40
     Arrays
    0.39
     shower
    0.38
    POSITIVE LOGITS
    namespace
    0.46
    iron
    0.44
    wheels
    0.42
    umpul
    0.39
    desktop
    0.39
    limit
    0.39
    limits
    0.38
     الحل
    0.38
    bang
    0.37
    LIMIT
    0.37
    Act Density 0.005%

    No Known Activations