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

    Neuronpedia

    INDEX
    Explanations

    build tools and dependencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Robb
    0.80
     preoccupied
    0.78
     étale
    0.73
     carne
    0.72
     handball
    0.72
     demoral
    0.72
     heterosexual
    0.72
     chan
    0.71
    ෙස
    0.71
    homotopic
    0.70
    POSITIVE LOGITS
    Maven
    2.10
     Maven
    2.05
     maven
    1.84
    maven
    1.78
     mvn
    1.47
     Gradle
    1.45
     jars
    1.45
     POM
    1.43
    Gradle
    1.43
    jar
    1.43
    Act Density 0.071%

    No Known Activations