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

    Neuronpedia

    INDEX
    Explanations

    irrational number approximations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     complejo
    -0.09
     geothermal
    -0.08
     complexo
    -0.08
    _sal
    -0.08
     workloads
    -0.08
     Promo
    -0.08
    otores
    -0.08
     пля
    -0.07
     complex
    -0.07
     sticker
    -0.07
    POSITIVE LOGITS
     지도
    0.08
     discre
    0.08
     محسوس
    0.08
    δ
    0.08
     수준
    0.08
    (delta
    0.08
    idak
    0.08
    arlu
    0.08
     magari
    0.08
     perturb
    0.07
    Act Density 0.012%

    No Known Activations