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

    Neuronpedia

    INDEX
    Explanations

    Research/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    备
    -0.07
    野
    -0.07
    指令
    -0.07
     Animal
    -0.07
     LF
    -0.07
    冷链
    -0.07
     dementia
    -0.06
     device
    -0.06
    輝
    -0.06
    دارة
    -0.06
    POSITIVE LOGITS
     Pete
    0.07
     schö
    0.07
    -kit
    0.07
    интер
    0.07
    にく
    0.07
     tatto
    0.07
     ресторан
    0.07
    楼主
    0.07
    �
    0.06
    etable
    0.06
    Act Density 0.101%

    No Known Activations