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

    Neuronpedia

    INDEX
    Explanations

    legal disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Украин
    -0.08
     Muscle
    -0.07
     Featuring
    -0.07
    员工
    -0.07
    しか
    -0.06
    Partner
    -0.06
    -series
    -0.06
    inventory
    -0.06
     Argentine
    -0.06
     muscular
    -0.06
    POSITIVE LOGITS
    issing
    0.08
    쥘
    0.08
    氨酸
    0.08
    подоб
    0.08
     Bray
    0.07
    שינוי
    0.07
     lj
    0.07
    慈悲
    0.07
    (Spring
    0.07
    🌷
    0.07
    Act Density 0.007%

    No Known Activations