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

    Neuronpedia

    INDEX
    Explanations

    introducing abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kittens
    0.87
     tinkering
    0.86
     verhindert
    0.85
     puppies
    0.85
     milkshake
    0.85
     robbing
    0.83
     kitten
    0.82
     puppy
    0.82
     kada
    0.82
     kneading
    0.82
    POSITIVE LOGITS
     hereinafter
    2.37
    hereafter
    2.35
    hereinafter
    2.32
    referred
    2.03
     hereafter
    2.01
     henceforth
    1.75
    简称
    1.61
     referred
    1.56
     herein
    1.48
    hence
    1.43
    Act Density 0.095%

    No Known Activations