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

    Neuronpedia

    INDEX
    Explanations

    Debug

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /slick
    -0.07
     Providers
    -0.07
    脔
    -0.07
     UIEdgeInsets
    -0.07
    辽宁省
    -0.07
    管理中心
    -0.07
     reliant
    -0.07
    ィ
    -0.06
    薅
    -0.06
    >↵
    -0.06
    POSITIVE LOGITS
     belle
    0.07
     обо
    0.07
    .Role
    0.07
    Early
    0.06
    .Co
    0.06
    aga
    0.06
     проблемы
    0.06
    离开了
    0.06
     callback
    0.06
     الحق
    0.06
    Act Density 0.003%

    No Known Activations