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

    Neuronpedia

    INDEX
    Explanations

    Here's a breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     몇
    0.81
     useless
    0.73
    mesinin
    0.72
     few
    0.71
     kilku
    0.71
     encouraging
    0.70
    몇
    0.70
     bow
    0.69
     मॉडलिंग
    0.68
     ngu
    0.68
    POSITIVE LOGITS
    ocommit
    0.76
    Craft
    0.71
    Deleg
    0.70
    navbarNav
    0.65
     comprehensively
    0.64
    appid
    0.64
    лур
    0.63
    📚
    0.63
    setFixedHeight
    0.63
     Patria
    0.62
    Act Density 0.223%

    No Known Activations