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

    Neuronpedia

    INDEX
    Explanations

    Car maintenance intervals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ла
    -0.10
     nền
    -0.08
    parency
    -0.08
     помогают
    -0.08
     настроение
    -0.08
    lež
    -0.08
     помог
    -0.08
     mở
    -0.08
     있으며
    -0.07
     chilled
    -0.07
    POSITIVE LOGITS
     kilom
    0.08
     zerst
    0.08
     kòm
    0.08
     Qualitäts
    0.08
     Shipping
    0.08
     pci
    0.08
     Mileage
    0.07
     किलो
    0.07
     crushing
    0.07
     Prüf
    0.07
    Act Density 0.004%

    No Known Activations