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

    Neuronpedia

    INDEX
    Explanations

    menu choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mengirim
    -0.88
     mengirimkan
    -0.88
    chaik
    -0.87
     publiée
    -0.85
     mariée
    -0.85
     vermelha
    -0.83
    ության
    -0.83
    addParameter
    -0.82
    натор
    -0.81
    ondata
    -0.81
    POSITIVE LOGITS
     menu
    3.25
     option
    2.70
     choice
    2.67
    menu
    2.63
    Menu
    2.59
     options
    2.44
     Menu
    2.44
     choices
    2.30
    choice
    2.17
    option
    2.16
    Act Density 0.019%

    No Known Activations