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

    Neuronpedia

    INDEX
    Explanations

    Code and data structures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UPDATED
    -0.08
    阻碍
    -0.07
     mirrored
    -0.07
    姤
    -0.06
     med
    -0.06
     метод
    -0.06
    天地
    -0.06
     hosted
    -0.06
    ophobic
    -0.06
     tabIndex
    -0.06
    POSITIVE LOGITS
    FirstName
    0.07
    (sem
    0.07
    hoa
    0.07
    (AP
    0.06
    得多
    0.06
    (Role
    0.06
    蝴
    0.06
    GenerationStrategy
    0.06
    ℬ
    0.06
    糖尿病
    0.06
    Act Density 0.003%

    No Known Activations