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

    Neuronpedia

    INDEX
    Explanations

    generating numerical sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     [][]
    0.77
     parsing
    0.73
     式
    0.72
    找到
    0.68
     finding
    0.68
     finds
    0.65
     trova
    0.65
    找不到
    0.65
     bö
    0.65
     find
    0.65
    POSITIVE LOGITS
    linspace
    0.95
     Ranges
    0.93
    Fill
    0.91
    Range
    0.89
     ranging
    0.88
    range
    0.88
    Repe
    0.88
    zeros
    0.87
     repeated
    0.87
    arange
    0.86
    Act Density 0.327%

    No Known Activations