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

    Neuronpedia

    INDEX
    Explanations

    code concerning file permissions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trif
    -0.07
     lm
    -0.07
     ig
    -0.06
    reservation
    -0.06
    endency
    -0.06
    straints
    -0.06
     Christians
    -0.06
    ích
    -0.06
    @Inject
    -0.06
     getters
    -0.06
    POSITIVE LOGITS
     vào
    0.06
     Pen
    0.06
     يع
    0.06
    grpc
    0.06
     поль
    0.06
     recycl
    0.06
    hunter
    0.06
     misd
    0.06
     трен
    0.06
    λο
    0.06
    Act Density 0.010%

    No Known Activations