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

    Neuronpedia

    INDEX
    Explanations

    verein, bereit, bereich

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sh
    -0.14
    so
    -0.12
    ship
    -0.11
    ron
    -0.11
    res
    -0.11
     Gong
    -0.10
     UD
    -0.10
    YSTEM
    -0.09
    sets
    -0.09
    red
    -0.09
    POSITIVE LOGITS
     Bere
    0.12
    itz
    0.11
    auc
    0.10
    bere
    0.10
    ÅĻik
    0.10
    uter
    0.10
     uncon
    0.09
    aved
    0.09
    itle
    0.09
    ::|
    0.09
    Act Density 0.018%

    No Known Activations