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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parliamentary
    -0.07
    едаг
    -0.07
    。あ
    -0.06
     eax
    -0.06
     dział
    -0.06
     humanitarian
    -0.06
    Meeting
    -0.06
     governments
    -0.06
     ترین
    -0.06
     zg
    -0.06
    POSITIVE LOGITS
    Obj
    0.07
    .Up
    0.07
     Sky
    0.07
     уд
    0.06
    	sql
    0.06
    лег
    0.06
    ète
    0.06
     Card
    0.06
    ملة
    0.06
    _paths
    0.06
    Act Density 0.036%

    No Known Activations