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

    Neuronpedia

    INDEX
    Explanations

    balancing/algorithms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accords
    -0.09
     Transit
    -0.08
     انتقال
    -0.08
    Transit
    -0.08
     hebt
    -0.08
    apolis
    -0.08
     يمن
    -0.08
    ampani
    -0.08
     يعتمد
    -0.08
    FUN
    -0.08
    POSITIVE LOGITS
     analyze
    0.08
     disclaim
    0.08
     Tail
    0.07
     constantly
    0.07
     הגוף
    0.07
     obsess
    0.07
     tail
    0.07
    (iv
    0.07
     ulu
    0.07
     araw
    0.07
    Act Density 0.001%

    No Known Activations