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

    Neuronpedia

    INDEX
    Explanations

    explaining definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dovrà
    0.54
     Será
    0.47
     tendremos
    0.46
     terão
    0.46
     deberán
    0.44
     deberá
    0.44
     będzie
    0.44
    ಿಸಿದ್ದರು
    0.44
    နိုင်
    0.43
     considerazione
    0.43
    POSITIVE LOGITS
     definition
    0.91
    Definition
    0.90
     Definition
    0.89
    definition
    0.86
     definitions
    0.82
     définition
    0.82
    什么是
    0.79
     परिभाषा
    0.79
    定義
    0.78
     definición
    0.77
    Act Density 1.015%

    No Known Activations