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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    回来
    -0.06
    (Table
    -0.06
    _var
    -0.06
     Topic
    -0.06
    ])*
    -0.06
    ivities
    -0.06
     Evo
    -0.06
     Control
    -0.06
    ancel
    -0.06
     было
    -0.06
    POSITIVE LOGITS
     Tyr
    0.08
     Kentucky
    0.08
     alum
    0.07
    rysler
    0.07
    Exiting
    0.06
    σε
    0.06
    _Act
    0.06
    (java
    0.06
     rightful
    0.06
    _CT
    0.06
    Act Density 0.003%

    No Known Activations