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

    Neuronpedia

    INDEX
    Explanations

    common

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Norte
    -0.09
     Aula
    -0.08
    indu
    -0.08
     cielo
    -0.08
     Infantil
    -0.08
    Ñ
    -0.08
     princípio
    -0.07
    ’on
    -0.07
    ació
    -0.07
     инструк
    -0.07
    POSITIVE LOGITS
     pitfalls
    0.10
     frequently
    0.08
     häufig
    0.08
     দ্ব
    0.08
     боли
    0.08
    шен
    0.08
     comunes
    0.08
     recurrence
    0.08
    ภัย
    0.08
     recurrent
    0.08
    Act Density 0.011%

    No Known Activations