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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    producer
    -0.07
    .Language
    -0.07
     ole
    -0.07
    ρας
    -0.06
     Robbie
    -0.06
     Magic
    -0.06
    Development
    -0.06
    _production
    -0.06
     encountered
    -0.06
     HALF
    -0.06
    POSITIVE LOGITS
    rador
    0.07
     ignor
    0.06
     safeg
    0.06
     ofere
    0.06
    :System
    0.06
     Leben
    0.06
    zb
    0.06
     useEffect
    0.06
    .setViewportView
    0.06
    ibrator
    0.06
    Act Density 0.177%

    No Known Activations