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

    Neuronpedia

    INDEX
    Explanations

    SonarQube

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     butterflies
    0.41
    पल
    0.38
     monomial
    0.36
     roasting
    0.36
     cremation
    0.36
    स्फोट
    0.35
     monolayer
    0.35
    花
    0.35
    strap
    0.34
     sublim
    0.34
    POSITIVE LOGITS
     sonar
    0.80
    Sonar
    0.75
    sonar
    0.70
     Son
    0.55
    Debt
    0.50
     debt
    0.49
     سون
    0.48
     Debt
    0.47
     deuda
    0.46
     ANALYSIS
    0.46
    Act Density 0.003%

    No Known Activations