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

    Neuronpedia

    INDEX
    Explanations

    azon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    APPLICATION
    -0.07
     Pork
    -0.06
     gratuito
    -0.06
    legal
    -0.06
     iktidar
    -0.06
     граж
    -0.06
    陶
    -0.06
    ونی
    -0.06
     oyuncu
    -0.06
    лекс
    -0.06
    POSITIVE LOGITS
     type
    0.10
     Types
    0.09
     sorts
    0.09
     types
    0.08
     вида
    0.08
     kind
    0.07
    tipo
    0.07
     Type
    0.07
     виды
    0.07
    Tipo
    0.07
    Act Density 0.047%

    No Known Activations