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

    Neuronpedia

    INDEX
    Explanations

    code library imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ות
    0.71
     Keep
    0.66
    Keep
    0.65
     Tomb
    0.61
    鹫
    0.59
     porn
    0.58
     والج
    0.58
     حدا
    0.58
    并在
    0.58
    ನ್ನಡ
    0.58
    POSITIVE LOGITS
     SwiftUI
    1.30
    stdio
    1.23
     bpy
    1.14
     UIKit
    1.11
    flutter
    1.07
     Vue
    1.07
    React
    1.04
    pulumi
    1.02
     viewDidLoad
    1.01
    lwjgl
    1.01
    Act Density 0.110%

    No Known Activations