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

    Neuronpedia

    INDEX
    Explanations

    mass units (mg, grams)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     அதனால்
    1.49
    ﺮ
    1.41
     Счетчик
    1.39
    TestSource
    1.36
    ﻲ
    1.36
     enhancing
    1.35
    idemargin
    1.35
     deregulation
    1.32
     Nella
    1.31
     Warum
    1.30
    POSITIVE LOGITS
    lar
    1.33
    ो
    1.32
     keer
    1.27
    Nous
    1.20
    其
    1.20
    larımız
    1.15
    Needless
    1.15
    celles
    1.14
    νης
    1.12
    rk
    1.12
    Act Density 0.013%

    No Known Activations