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

    Neuronpedia

    INDEX
    Explanations

    smooth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thrilling
    -0.08
    New
    -0.08
    pozn
    -0.07
    객
    -0.07
     ralent
    -0.07
    الج
    -0.07
     früher
    -0.07
     herkennen
    -0.07
     adaptation
    -0.07
     Herz
    -0.07
    POSITIVE LOGITS
    ообраз
    0.08
     Scotia
    0.08
     celebrar
    0.08
     Cambodian
    0.08
     workspace
    0.08
     vende
    0.08
     fm
    0.08
     Natalie
    0.08
     બનાવવા
    0.08
     представ
    0.08
    Act Density 0.002%

    No Known Activations