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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Prostate
    0.74
     prostate
    0.70
     limb
    0.69
    tests
    0.67
    PrivateKey
    0.66
    UnitTest
    0.66
    Tests
    0.65
     Toxicology
    0.65
     법
    0.64
    Toilet
    0.64
    POSITIVE LOGITS
     stadium
    0.69
    广播
    0.69
     Rac
    0.68
     sted
    0.68
     фикси
    0.67
     fixed
    0.67
     Fixed
    0.67
     carriers
    0.66
     arreg
    0.65
     surviv
    0.62
    Act Density 0.002%

    No Known Activations