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

    Neuronpedia

    INDEX
    Explanations

    quotation marks, parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𝐲
    -0.07
    🐐
    -0.07
     tweeting
    -0.07
    -player
    -0.07
     travelers
    -0.07
    陬
    -0.07
    $stmt
    -0.07
    相比于
    -0.06
    欹
    -0.06
    		
↵
↵
    -0.06
    POSITIVE LOGITS
    asia
    0.08
     кли
    0.07
    Deletes
    0.07
    inyin
    0.07
     einen
    0.07
    il
    0.07
    ッシ
    0.07
    ony
    0.07
     CLASS
    0.07
    Stores
    0.07
    Act Density 0.002%

    No Known Activations