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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    🥣
    0.35
     hilfre
    0.34
     voluntad
    0.33
     sinnv
    0.33
     mögliche
    0.33
     দাবী
    0.32
     জিনিসের
    0.32
     ardent
    0.32
    StoredKeys
    0.32
     Validación
    0.32
    POSITIVE LOGITS
    <unused2110>
    0.39
    -
    0.38
    ப்
    0.34
    ových
    0.34
    related
    0.32
    -,
    0.32
     ­
    0.29
    ੱ
    0.29
    <unused2143>
    0.29
     dieses
    0.29
    Act Density 2.271%

    No Known Activations