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

    Neuronpedia

    INDEX
    Explanations

    many different factors or ways

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Certain
    1.17
    Some
    1.03
    some
    0.95
     Certain
    0.95
    Most
    0.91
     certaine
    0.89
    某些
    0.86
    Two
    0.85
     Some
    0.85
    Something
    0.83
    POSITIVE LOGITS
     iterations
    1.13
     different
    1.05
     layers
    1.04
     facets
    1.03
     tweaks
    1.02
     dozen
    1.01
     permutations
    0.98
     avenues
    0.97
     possibilities
    0.94
     opportunities
    0.93
    Act Density 0.310%

    No Known Activations