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

    Neuronpedia

    INDEX
    Explanations

    function and constructor definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     experiencing
    0.70
     flash
    0.69
     ripple
    0.68
    elligence
    0.65
     beaming
    0.64
     beacon
    0.64
     releases
    0.63
     Dramatic
    0.61
    quakes
    0.61
    ình
    0.60
    POSITIVE LOGITS
    Initialization
    0.99
    Constructor
    0.97
    viewDidLoad
    0.95
     Initialization
    0.94
    Before
    0.94
    override
    0.93
    Init
    0.93
     constructor
    0.93
    Initialize
    0.92
     ngOnInit
    0.91
    Act Density 0.115%

    No Known Activations