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

    Neuronpedia

    INDEX
    Explanations

    stage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Orleans
    -0.06
    manız
    -0.06
     Nazis
    -0.06
    Щ
    -0.06
    amacare
    -0.06
     Вот
    -0.06
    альным
    -0.06
    Upon
    -0.06
     نفسه
    -0.06
    .restaurant
    -0.06
    POSITIVE LOGITS
     stage
    0.15
     onstage
    0.14
     Stage
    0.08
     stages
    0.08
    -stage
    0.07
     curtain
    0.07
    stage
    0.07
     structure
    0.07
     develop
    0.07
     profil
    0.07
    Act Density 0.005%

    No Known Activations