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

    Neuronpedia

    INDEX
    Explanations

    Joy in every bite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    在北京
    0.44
     rebellion
    0.38
     incineration
    0.38
     cancerous
    0.37
     beton
    0.37
     cancer
    0.37
     inferred
    0.36
     illegal
    0.36
     mandible
    0.36
     मणिपुर
    0.35
    POSITIVE LOGITS
     سیل
    0.45
     للا
    0.43
    প্ল
    0.41
    Dimethyl
    0.39
     Repo
    0.39
    鯢
    0.39
     spezial
    0.39
    Repo
    0.38
    CONDUCT
    0.38
     풀어
    0.38
    Act Density 0.002%

    No Known Activations