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

    Neuronpedia

    INDEX
    Explanations

    Specific details

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ihr
    -0.07
     والن
    -0.06
     přen
    -0.06
    َد
    -0.06
     транс
    -0.06
     três
    -0.06
     briefed
    -0.06
     البد
    -0.06
     longest
    -0.06
    	Item
    -0.06
    POSITIVE LOGITS
     búsqueda
    0.06
     gl
    0.06
    왔다
    0.06
    -sl
    0.06
     {\↵
    0.06
    /owl
    0.06
    %^
    0.06
    .foundation
    0.05
    ases
    0.05
    .angular
    0.05
    Act Density 0.097%

    No Known Activations