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

    Neuronpedia

    INDEX
    Explanations

    chair

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ttle
    -0.08
    оложение
    -0.08
     δικ
    -0.07
     పవ
    -0.07
     entered
    -0.07
     cached
    -0.07
    Power
    -0.07
     quyền
    -0.07
    θούν
    -0.07
    ARM
    -0.07
    POSITIVE LOGITS
     unavoidable
    0.08
     greifen
    0.08
     präsentieren
    0.08
     manufacturing
    0.07
     manufactured
    0.07
     giet
    0.07
     uncomplicated
    0.07
     výro
    0.07
     Orang
    0.07
     noodles
    0.07
    Act Density 0.001%

    No Known Activations