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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations/Acronyms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     following
    -0.08
     Scores
    -0.07
     freezing
    -0.07
     architecture
    -0.07
     Kir
    -0.07
    ']]↵
    -0.07
     McCarthy
    -0.07
     conquered
    -0.07
     vhod
    -0.07
     Fal
    -0.07
    POSITIVE LOGITS
    iej
    0.08
     زنده
    0.07
     реє
    0.07
    оке
    0.07
    ensburg
    0.07
    ersh
    0.06
     стек
    0.06
    ombok
    0.06
    -к
    0.06
     período
    0.06
    Act Density 0.072%

    No Known Activations