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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     رأس
    -0.08
    )];↵
    -0.08
     기타
    -0.08
     doj
    -0.08
    ));↵↵//
    -0.07
    _Message
    -0.07
     };↵↵//
    -0.07
     செய்திகள்
    -0.07
    };↵//
    -0.07
     networking
    -0.07
    POSITIVE LOGITS
     ühe
    0.09
     discrete
    0.09
     daarvoor
    0.09
    olan
    0.08
     alternatively
    0.08
    عى
    0.08
     sådan
    0.08
    one
    0.08
    uhake
    0.08
     sogen
    0.08
    Act Density 0.043%

    No Known Activations