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

    Neuronpedia

    INDEX
    Explanations

    used car condition and maintenance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scalar
    0.48
     softmax
    0.48
    scalar
    0.45
     contexts
    0.44
     dimensionless
    0.43
    溶液
    0.43
     monadic
    0.43
    Scalar
    0.43
     hypothesized
    0.41
    contexts
    0.40
    POSITIVE LOGITS
     mechanically
    0.79
     repairs
    0.78
     mechanical
    0.75
     drivetrain
    0.75
     odometer
    0.74
     mileage
    0.71
    mechanical
    0.69
     owners
    0.68
     powertrain
    0.67
     vehicles
    0.67
    Act Density 0.015%

    No Known Activations