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

    Neuronpedia

    INDEX
    Explanations

    countries, animals, games, specific stores

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sensibilities
    0.39
     implementations
    0.38
     Ansatz
    0.38
     endpoints
    0.36
     assessments
    0.36
     optimizations
    0.35
     suboptimal
    0.35
     nuances
    0.35
     접근
    0.35
     recommendations
    0.34
    POSITIVE LOGITS
    䀼
    0.42
     Railroad
    0.41
     Depot
    0.40
     Pork
    0.40
     Jokes
    0.40
     Medica
    0.38
     Juice
    0.38
    قلال
    0.38
     Lawn
    0.38
     Dye
    0.38
    Act Density 0.192%

    No Known Activations