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

    Neuronpedia

    INDEX
    Explanations

    file extensions and tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kubernetes
    0.86
     DevOps
    0.78
     HubSpot
    0.75
     Azure
    0.72
     TypeScript
    0.71
     ADHD
    0.70
     Kotlin
    0.69
     Teknik
    0.69
     Figma
    0.69
     TensorFlow
    0.68
    POSITIVE LOGITS
    ctrl
    0.98
    q
    0.95
    _
    0.95
    avg
    0.95
    conv
    0.92
    cmd
    0.92
    msg
    0.92
    info
    0.91
    ctx
    0.91
    seq
    0.90
    Act Density 0.331%

    No Known Activations