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

    Neuronpedia

    INDEX
    Explanations

    relationships between things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scram
    -0.07
    ugas
    -0.06
     Radi
    -0.06
     uprav
    -0.06
     yields
    -0.06
     JLabel
    -0.06
    Пр
    -0.06
     Wis
    -0.06
     Rwanda
    -0.06
    ाओ
    -0.06
    POSITIVE LOGITS
    (Runtime
    0.07
     下跌
    0.07
    709
    0.07
    ิษ
    0.06
     прежде
    0.06
     прибор
    0.06
     допомаг
    0.06
     Jackets
    0.06
    -shadow
    0.06
    �
    0.06
    Act Density 0.003%

    No Known Activations