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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     responses
    0.52
     Response
    0.49
     Responses
    0.47
     response
    0.45
     ViewBag
    0.42
     گا۔
    0.41
     कमांड
    0.40
     प्राणियों
    0.39
     ORGANIZATION
    0.39
     পারে
    0.38
    POSITIVE LOGITS
    X
    0.58
     X
    0.57
    --
    0.52
    -”
    0.52
    ,-
    0.50
    having
    0.50
    —-
    0.49
    simplify
    0.49
     simplified
    0.48
     having
    0.46
    Act Density 0.000%

    No Known Activations