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

    Neuronpedia

    INDEX
    Explanations

    implementation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     delegated
    -0.08
     температура
    -0.08
     توص
    -0.08
    (..
    -0.08
    ಂತಹ
    -0.08
     recipes
    -0.08
     depender
    -0.07
     зв
    -0.07
     советы
    -0.07
     Empfehlungen
    -0.07
    POSITIVE LOGITS
     Peyton
    0.07
     lucky
    0.07
    नों
    0.07
    ienze
    0.07
     loader
    0.07
    0.07
     Scoop
    0.07
     dumb
    0.07
    nia
    0.07
     kail
    0.07
    Act Density 0.001%
    No Known Activations