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

    Neuronpedia

    INDEX
    Explanations

    Affirmations/Negations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ylinder
    -0.07
     sen
    -0.07
    	tab
    -0.06
     cent
    -0.06
     خواب
    -0.06
     caliber
    -0.06
    ़र
    -0.06
    -Con
    -0.06
    ENO
    -0.06
    Trump
    -0.06
    POSITIVE LOGITS
    ické
    0.06
    ========
    0.06
    scaled
    0.06
     ژوئ
    0.06
    �
    0.06
     установлен
    0.06
    forcer
    0.06
    annabin
    0.06
    Months
    0.06
     leggings
    0.06
    Act Density 0.004%

    No Known Activations