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

    Neuronpedia

    INDEX
    Explanations

    city names and architecture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     नांदेड
    0.44
    青森
    0.42
    Sony
    0.42
    瓷
    0.39
    Victoria
    0.38
    ッティング
    0.38
     মহারা
    0.37
     দিল্লির
    0.37
    􀂾
    0.37
    Maharashtra
    0.36
    POSITIVE LOGITS
    부산
    0.65
     부산
    0.62
     liver
    0.45
     Bous
    0.41
     hormon
    0.41
    [(
    0.40
    ophon
    0.40
     Busan
    0.40
     PMC
    0.40
     DSP
    0.40
    Act Density 0.012%

    No Known Activations