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

    Neuronpedia

    INDEX
    Explanations

    expensive, overpriced, high cost

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inexpensive
    0.44
    ogenic
    0.42
     divaricatis
    0.42
     Boltzmann
    0.42
     volc
    0.40
     async
    0.39
     stochastic
    0.39
     carcinogenesis
    0.39
     অ্যান্ট
    0.38
     engages
    0.37
    POSITIVE LOGITS
     unjustified
    0.60
     justified
    0.59
     overpriced
    0.57
     justify
    0.55
     inflated
    0.48
     גבוה
    0.48
     висо
    0.48
     high
    0.47
     robbery
    0.47
     justification
    0.46
    Act Density 0.040%

    No Known Activations