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

    Neuronpedia

    INDEX
    Explanations

    techniques, trends, object, seasonal, beginner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    issory
    0.45
    dihydro
    0.40
    UpdatedAt
    0.39
     surjective
    0.38
     ataupun
    0.38
    compressible
    0.37
    或是
    0.37
     rattles
    0.37
    Abroad
    0.36
    tum
    0.36
    POSITIVE LOGITS
     Genre
    0.46
     sním
    0.41
    ﻡ
    0.39
     specialize
    0.39
    ຫ
    0.38
     genre
    0.38
     parque
    0.38
    incu
    0.38
     hijack
    0.38
    מש
    0.37
    Act Density 0.001%

    No Known Activations