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

    Neuronpedia

    INDEX
    Explanations

    github repositories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     न्यूज़
    0.75
     Qui
    0.74
     rice
    0.72
     Tilly
    0.69
     tease
    0.68
     tz
    0.67
     qui
    0.66
     gle
    0.66
     practicing
    0.66
     neutrinos
    0.65
    POSITIVE LOGITS
    Project
    0.89
    Projects
    0.88
    ProjectPath
    0.85
     Project
    0.84
     IDE
    0.82
    Library
    0.80
     IntelliJ
    0.79
     Projects
    0.77
    project
    0.76
    Solution
    0.75
    Act Density 0.065%

    No Known Activations