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

    Neuronpedia

    INDEX
    Explanations

    Java/Kotlin package declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    React
    0.91
    svelte
    0.88
     React
    0.86
     java
    0.83
    setTimeout
    0.78
    *
    0.75
     react
    0.73
    {
    0.71
     angular
    0.70
    dotenv
    0.69
    POSITIVE LOGITS
     br
    0.95
    ru
    0.93
     stacks
    0.90
     ru
    0.86
     handlers
    0.86
     hr
    0.84
     arrays
    0.83
     Ru
    0.82
     pack
    0.81
     furnishes
    0.81
    Act Density 0.000%

    No Known Activations