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

    Neuronpedia

    INDEX
    Explanations

    expensive or pricey

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    decoder
    0.43
     `'\\
    0.40
    ামো
    0.40
    INDIA
    0.39
    वृद्धि
    0.38
    myapp
    0.37
    ᵚ
    0.37
    mour
    0.37
     Ashwin
    0.37
    rable
    0.36
    POSITIVE LOGITS
    -
    0.46
     season
    0.42
     p
    0.42
     du
    0.42
     n
    0.42
     person
    0.41
     campus
    0.40
     agak
    0.40
    )
    0.39
     .
    0.39
    Act Density 0.000%

    No Known Activations