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

    Neuronpedia

    INDEX
    Explanations

    Python class method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Automatically
    0.98
     IntelliJ
    0.93
    Changing
    0.92
     Reflection
    0.91
     Perfection
    0.90
     Recreation
    0.90
     Specifically
    0.88
     Harvesting
    0.87
    Specifically
    0.87
    Photograph
    0.86
    POSITIVE LOGITS
    num
    1.21
    _,
    1.19
     num
    1.11
     _,
    1.09
    idx
    1.04
     r
    1.04
    curr
    1.04
    temp
    1.02
     tmp
    1.02
     y
    1.01
    Act Density 0.230%

    No Known Activations