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

    Neuronpedia

    INDEX
    Explanations

    Kubernetes ingress configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Conclusions
    0.41
    Cv
    0.40
     Literary
    0.40
    Motivational
    0.39
     സൃ
    0.39
     Applies
    0.38
    ကျင်
    0.38
     วัน
    0.38
     Unemployment
    0.37
    俶
    0.37
    POSITIVE LOGITS
    EntryPoint
    0.44
     garages
    0.41
     cold
    0.40
     ped
    0.40
     host
    0.38
     comer
    0.37
    ExceptionHandler
    0.37
     department
    0.36
     número
    0.36
     🤔
    0.36
    Act Density 0.001%

    No Known Activations