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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hour
    -0.07
    routing
    -0.07
     Bilim
    -0.07
    nection
    -0.07
     Effects
    -0.06
     bad
    -0.06
     Ak
    -0.06
     effects
    -0.06
    Arthur
    -0.06
     frustrated
    -0.06
    POSITIVE LOGITS
    	constexpr
    0.07
     mír
    0.06
     фев
    0.06
     κορ
    0.06
    έν
    0.06
     khả
    0.06
    ứa
    0.06
     겨
    0.06
    \Auth
    0.06
    decl
    0.06
    Act Density 0.067%

    No Known Activations