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

    Neuronpedia

    INDEX
    Explanations

    investigations and news

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Scope
    -0.08
    says
    -0.07
     defends
    -0.07
     تع
    -0.07
    Sequential
    -0.07
    那
    -0.07
     KERNEL
    -0.07
    authentication
    -0.06
     d
    -0.06
    Property
    -0.06
    POSITIVE LOGITS
     ราคา
    0.07
     dpi
    0.06
     Λ
    0.06
    essor
    0.06
    .modelo
    0.06
     Clover
    0.06
     serviços
    0.06
     일반
    0.06
    RouterModule
    0.06
     DateFormatter
    0.06
    Act Density 0.045%

    No Known Activations