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

    Neuronpedia

    INDEX
    Explanations

    code and technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Failure
    -0.07
     meilleur
    -0.07
     crumbs
    -0.07
    	items
    -0.06
    ована
    -0.06
    uer
    -0.06
     Raum
    -0.06
     productService
    -0.06
     bridal
    -0.06
     bringing
    -0.06
    POSITIVE LOGITS
    突然
    0.06
     profitability
    0.06
    ійного
    0.06
    ـ
    0.06
     кисл
    0.06
    	   ↵
    0.06
    idental
    0.06
    ldr
    0.06
    �
    0.06
    _bel
    0.06
    Act Density 0.005%

    No Known Activations