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

    Neuronpedia

    INDEX
    Explanations

    code fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Menus
    -0.08
    	opts
    -0.07
     doub
    -0.07
     ducks
    -0.07
    ዮ
    -0.07
     prose
    -0.07
    ,proto
    -0.07
     Phones
    -0.07
    };
    -0.07
     Tanz
    -0.07
    POSITIVE LOGITS
    Item
    0.07
    CC
    0.07
    .ra
    0.07
    _error
    0.07
    九
    0.07
    夫人
    0.07
    篇
    0.06
     désorm
    0.06
    .lesson
    0.06
     prior
    0.06
    Act Density 0.191%

    No Known Activations