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

    Neuronpedia

    INDEX
    Explanations

    File

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hiển
    -0.07
     놓
    -0.07
     未
    -0.07
    �
    -0.06
    cone
    -0.06
    普
    -0.06
     次
    -0.06
    conc
    -0.06
     gå
    -0.06
     McGr
    -0.06
    POSITIVE LOGITS
    opus
    0.07
     kaliteli
    0.07
    redentials
    0.07
     struk
    0.07
    alon
    0.07
     formulario
    0.07
    оги
    0.07
    navbar
    0.07
     Argentine
    0.06
    gradation
    0.06
    Act Density 0.003%

    No Known Activations