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

    Neuronpedia

    INDEX
    Explanations

    program arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    []
    0.82
    []=
    0.80
    [][
    0.77
    [],
    0.73
    [][]
    0.70
     []
    0.66
    [];
    0.64
    []{
    0.56
    []>
    0.50
     [][]
    0.50
    POSITIVE LOGITS
     args
    0.71
    args
    0.64
     _)
    0.55
    argv
    0.54
     Args
    0.52
     EventArgs
    0.51
    ary
    0.46
     arguments
    0.45
    Args
    0.44
     argv
    0.44
    Act Density 0.001%

    No Known Activations