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

    Neuronpedia

    INDEX
    Explanations

    programming questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Industry
    -0.06
    ицин
    -0.06
    ORN
    -0.06
     Manson
    -0.06
     Üniversit
    -0.06
     WHETHER
    -0.06
     Memories
    -0.06
    Life
    -0.06
     Werner
    -0.06
     cocaine
    -0.06
    POSITIVE LOGITS
     nós
    0.06
     پایه
    0.06
    、《
    0.06
     Missile
    0.06
    asily
    0.06
     lining
    0.06
     نیم
    0.06
     esto
    0.05
    Сам
    0.05
     بين
    0.05
    Act Density 0.092%

    No Known Activations