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

    Neuronpedia

    INDEX
    Explanations

    design thinking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ajuste
    -0.08
     commissioning
    -0.08
    API
    -0.07
     metal
    -0.07
     га
    -0.07
     new
    -0.07
    ידה
    -0.07
     crispy
    -0.07
     ministry
    -0.07
     hiring
    -0.07
    POSITIVE LOGITS
     Danach
    0.09
     స్టార్
    0.09
     étoiles
    0.09
     genügend
    0.09
     Coupons
    0.08
     सित
    0.08
     Iterate
    0.08
    antas
    0.08
     inúmeras
    0.08
     छात्र
    0.08
    Act Density 0.006%

    No Known Activations