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

    Neuronpedia

    INDEX
    Explanations

    note

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     मुक्त
    -0.09
     juventud
    -0.08
    gratis
    -0.08
     التشغيل
    -0.08
     gratuitamente
    -0.08
     मुफ्त
    -0.08
     revan
    -0.08
     дешев
    -0.08
     玩
    -0.08
     carefree
    -0.08
    POSITIVE LOGITS
     quietly
    0.08
     sincere
    0.08
    usi
    0.07
     reputable
    0.07
     decent
    0.07
    ussi
    0.07
     sincerity
    0.07
    arii
    0.07
     tranquilo
    0.07
     requer
    0.07
    Act Density 0.176%

    No Known Activations